Beruflich Dokumente
Kultur Dokumente
memory References
O. Hasegawa2
Key Laboratory for Novel Software Technology, Nanjing University Science and Engineering Lab, Tokyo Institute of Technology
2 Imaging
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
What is SOINN
1 2
What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
4 5
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
What is SOINN
What is SOINN
SOINN: Self-organizing incremental neural network Represent the topological structure of the input data Realize online incremental learning
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
What is SOINN
What is SOINN
SOINN: Self-organizing incremental neural network Represent the topological structure of the input data Realize online incremental learning
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
What is SOINN
What is SOINN
SOINN: Self-organizing incremental neural network Represent the topological structure of the input data Realize online incremental learning
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
What is SOINN
What is SOINN
SOINN: Self-organizing incremental neural network Represent the topological structure of the input data Realize online incremental learning
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
1 2
What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
4 5
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOM(Self-Organizing Map): predene structure and size of the network NG(Neural Gas): predene the network size GNG(Growing Neural Gas): predene the network size; constant learning rate leads to non-stationary result.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOM(Self-Organizing Map): predene structure and size of the network NG(Neural Gas): predene the network size GNG(Growing Neural Gas): predene the network size; constant learning rate leads to non-stationary result.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOM(Self-Organizing Map): predene structure and size of the network NG(Neural Gas): predene the network size GNG(Growing Neural Gas): predene the network size; constant learning rate leads to non-stationary result.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOM(Self-Organizing Map): predene structure and size of the network NG(Neural Gas): predene the network size GNG(Growing Neural Gas): predene the network size; constant learning rate leads to non-stationary result.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Incremental learning: Learning new knowledge without destroy of old learned knowledge (Stability-Plasticity Dilemma) ART(Adaptive Resonance Theory): Need a user dened threshold. Multilayer Perceptrons: To learn new knowledge will destroy old knowledge Sub-network methods: Need plenty of storage
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Incremental learning: Learning new knowledge without destroy of old learned knowledge (Stability-Plasticity Dilemma) ART(Adaptive Resonance Theory): Need a user dened threshold. Multilayer Perceptrons: To learn new knowledge will destroy old knowledge Sub-network methods: Need plenty of storage
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Incremental learning: Learning new knowledge without destroy of old learned knowledge (Stability-Plasticity Dilemma) ART(Adaptive Resonance Theory): Need a user dened threshold. Multilayer Perceptrons: To learn new knowledge will destroy old knowledge Sub-network methods: Need plenty of storage
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Incremental learning: Learning new knowledge without destroy of old learned knowledge (Stability-Plasticity Dilemma) ART(Adaptive Resonance Theory): Need a user dened threshold. Multilayer Perceptrons: To learn new knowledge will destroy old knowledge Sub-network methods: Need plenty of storage
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Incremental learning: Learning new knowledge without destroy of old learned knowledge (Stability-Plasticity Dilemma) ART(Adaptive Resonance Theory): Need a user dened threshold. Multilayer Perceptrons: To learn new knowledge will destroy old knowledge Sub-network methods: Need plenty of storage
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Characteristics of SOINN
Neurons are self-organized with no predened network structure and size Adaptively nd suitable number of neurons for the network Realize online incremental learning without any priori condition Find typical prototypes for large-scale data set. Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Characteristics of SOINN
Neurons are self-organized with no predened network structure and size Adaptively nd suitable number of neurons for the network Realize online incremental learning without any priori condition Find typical prototypes for large-scale data set. Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Characteristics of SOINN
Neurons are self-organized with no predened network structure and size Adaptively nd suitable number of neurons for the network Realize online incremental learning without any priori condition Find typical prototypes for large-scale data set. Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Characteristics of SOINN
Neurons are self-organized with no predened network structure and size Adaptively nd suitable number of neurons for the network Realize online incremental learning without any priori condition Find typical prototypes for large-scale data set. Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Characteristics of SOINN
Neurons are self-organized with no predened network structure and size Adaptively nd suitable number of neurons for the network Realize online incremental learning without any priori condition Find typical prototypes for large-scale data set. Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Characteristics of SOINN
Neurons are self-organized with no predened network structure and size Adaptively nd suitable number of neurons for the network Realize online incremental learning without any priori condition Find typical prototypes for large-scale data set. Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
1 2
What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
4 5
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Adaptively updated threshold Between-class insertion Update weight of nodes Within-class insertion Remove noise nodes
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Adaptively updated threshold Between-class insertion Update weight of nodes Within-class insertion Remove noise nodes
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Adaptively updated threshold Between-class insertion Update weight of nodes Within-class insertion Remove noise nodes
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Adaptively updated threshold Between-class insertion Update weight of nodes Within-class insertion Remove noise nodes
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Adaptively updated threshold Between-class insertion Update weight of nodes Within-class insertion Remove noise nodes
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Adaptively updated threshold Between-class insertion Update weight of nodes Within-class insertion Remove noise nodes
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Adaptively updated threshold Between-class insertion Update weight of nodes Within-class insertion Remove noise nodes
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Initialize: Ti = + when node i is a new node. When i is winner or second winner, update Ti by
If i has neighbors, Ti is updated as the maximum distance between i and all of its neighbors. Ti = max ||Wi Wc ||
cNi
(1)
If i has no neighbors, Ti is updated as the minimum distance of i and all other nodes in network A. Ti = min ||Wi Wc ||
cA\{i }
(2)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Initialize: Ti = + when node i is a new node. When i is winner or second winner, update Ti by
If i has neighbors, Ti is updated as the maximum distance between i and all of its neighbors. Ti = max ||Wi Wc ||
cNi
(1)
If i has no neighbors, Ti is updated as the minimum distance of i and all other nodes in network A. Ti = min ||Wi Wc ||
cA\{i }
(2)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Initialize: Ti = + when node i is a new node. When i is winner or second winner, update Ti by
If i has neighbors, Ti is updated as the maximum distance between i and all of its neighbors. Ti = max ||Wi Wc ||
cNi
(1)
If i has no neighbors, Ti is updated as the minimum distance of i and all other nodes in network A. Ti = min ||Wi Wc ||
cA\{i }
(2)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Initialize: Ti = + when node i is a new node. When i is winner or second winner, update Ti by
If i has neighbors, Ti is updated as the maximum distance between i and all of its neighbors. Ti = max ||Wi Wc ||
cNi
(1)
If i has no neighbors, Ti is updated as the minimum distance of i and all other nodes in network A. Ti = min ||Wi Wc ||
cA\{i }
(2)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Initialize: Ti = + when node i is a new node. When i is winner or second winner, update Ti by
If i has neighbors, Ti is updated as the maximum distance between i and all of its neighbors. Ti = max ||Wi Wc ||
cNi
(1)
If i has no neighbors, Ti is updated as the minimum distance of i and all other nodes in network A. Ti = min ||Wi Wc ||
cA\{i }
(2)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Initialize: Ti = + when node i is a new node. When i is winner or second winner, update Ti by
If i has neighbors, Ti is updated as the maximum distance between i and all of its neighbors. Ti = max ||Wi Wc ||
cNi
(1)
If i has no neighbors, Ti is updated as the minimum distance of i and all other nodes in network A. Ti = min ||Wi Wc ||
cA\{i }
(2)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
(3)
min
||Wi Wj ||
(4)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
(3)
min
||Wi Wj ||
(4)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
(3)
min
||Wi Wj ||
(4)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
(3)
min
||Wi Wj ||
(4)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
(3)
min
||Wi Wj ||
(4)
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
min
db (Ck , Cl )
(5)
min
db (Ck , Cl )
(6)
If Tc is less than within-class distance dw , set Tc as the next minimum between-cluster distance. Tc = db (Ci2 , Cj2 ) =
k,l=1,...,Q,k=l,k=i1 ,l=j1
min
db (Ck , Cl )
(7)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
min
db (Ck , Cl )
(5)
min
db (Ck , Cl )
(6)
If Tc is less than within-class distance dw , set Tc as the next minimum between-cluster distance. Tc = db (Ci2 , Cj2 ) =
k,l=1,...,Q,k=l,k=i1 ,l=j1
min
db (Ck , Cl )
(7)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
min
db (Ck , Cl )
(5)
min
db (Ck , Cl )
(6)
If Tc is less than within-class distance dw , set Tc as the next minimum between-cluster distance. Tc = db (Ci2 , Cj2 ) =
k,l=1,...,Q,k=l,k=i1 ,l=j1
min
db (Ck , Cl )
(7)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
min
db (Ck , Cl )
(5)
min
db (Ck , Cl )
(6)
If Tc is less than within-class distance dw , set Tc as the next minimum between-cluster distance. Tc = db (Ci2 , Cj2 ) =
k,l=1,...,Q,k=l,k=i1 ,l=j1
min
db (Ck , Cl )
(7)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
min
db (Ck , Cl )
(5)
min
db (Ck , Cl )
(6)
If Tc is less than within-class distance dw , set Tc as the next minimum between-cluster distance. Tc = db (Ci2 , Cj2 ) =
k,l=1,...,Q,k=l,k=i1 ,l=j1
min
db (Ck , Cl )
(7)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
After the size of network becomes stable, ne tune the network stochastic approximation: a number of adaptation steps with a strength (t) decaying slowly but not too slowly, i.e., 2 t=1 (t) = , and t=1 (t) < . The harmonic series satises the conditions. 1 1 (t) = , t
F. Shen, O. Hasegawa
2 (t) =
1 100t
(10)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
After the size of network becomes stable, ne tune the network stochastic approximation: a number of adaptation steps with a strength (t) decaying slowly but not too slowly, i.e., 2 t=1 (t) = , and t=1 (t) < . The harmonic series satises the conditions. 1 1 (t) = , t
F. Shen, O. Hasegawa
2 (t) =
1 100t
(10)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
After the size of network becomes stable, ne tune the network stochastic approximation: a number of adaptation steps with a strength (t) decaying slowly but not too slowly, i.e., 2 t=1 (t) = , and t=1 (t) < . The harmonic series satises the conditions. 1 1 (t) = , t
F. Shen, O. Hasegawa
2 (t) =
1 100t
(10)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
After the size of network becomes stable, ne tune the network stochastic approximation: a number of adaptation steps with a strength (t) decaying slowly but not too slowly, i.e., 2 t=1 (t) = , and t=1 (t) < . The harmonic series satises the conditions. 1 1 (t) = , t
F. Shen, O. Hasegawa
2 (t) =
1 100t
(10)
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Single-layer SOINN
For topology representation, rst-layer is enough Within-class insertion slightly happened in rst-layer Using subclass and density to judge if connection is needed.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Single-layer SOINN
For topology representation, rst-layer is enough Within-class insertion slightly happened in rst-layer Using subclass and density to judge if connection is needed.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Single-layer SOINN
For topology representation, rst-layer is enough Within-class insertion slightly happened in rst-layer Using subclass and density to judge if connection is needed.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Single-layer SOINN
For topology representation, rst-layer is enough Within-class insertion slightly happened in rst-layer Using subclass and density to judge if connection is needed.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Single-layer SOINN
For topology representation, rst-layer is enough Within-class insertion slightly happened in rst-layer Using subclass and density to judge if connection is needed.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Single-layer SOINN
For topology representation, rst-layer is enough Within-class insertion slightly happened in rst-layer Using subclass and density to judge if connection is needed.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Conclusion of experiments: SOINN is able to Represent topology structure of input data. Realize incremental learning. AutomaticallyF.learnO.number of Self-organizing incremental neural network and its application nodes, de-noise, etc. Shen, Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Conclusion of experiments: SOINN is able to Represent topology structure of input data. Realize incremental learning. AutomaticallyF.learnO.number of Self-organizing incremental neural network and its application nodes, de-noise, etc. Shen, Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Conclusion of experiments: SOINN is able to Represent topology structure of input data. Realize incremental learning. AutomaticallyF.learnO.number of Self-organizing incremental neural network and its application nodes, de-noise, etc. Shen, Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Conclusion of experiments: SOINN is able to Represent topology structure of input data. Realize incremental learning. AutomaticallyF.learnO.number of Self-organizing incremental neural network and its application nodes, de-noise, etc. Shen, Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Conclusion of experiments: SOINN is able to Represent topology structure of input data. Realize incremental learning. AutomaticallyF.learnO.number of Self-organizing incremental neural network and its application nodes, de-noise, etc. Shen, Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Conclusion of experiments: SOINN is able to Represent topology structure of input data. Realize incremental learning. AutomaticallyF.learnO.number of Self-organizing incremental neural network and its application nodes, de-noise, etc. Shen, Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Conclusion of experiments: SOINN is able to Represent topology structure of input data. Realize incremental learning. AutomaticallyF.learnO.number of Self-organizing incremental neural network and its application nodes, de-noise, etc. Shen, Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN Training process of SOINN Similarity threshold for judging input data Learning rate Simple version of SOINN Simulation results
Conclusion of experiments: SOINN is able to Represent topology structure of input data. Realize incremental learning. AutomaticallyF.learnO.number of Self-organizing incremental neural network and its application nodes, de-noise, etc. Shen, Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
1 2
What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
4 5
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn number of classes of input data Clustering with no priori knowledge Topology representation Realize real-time incremental learning Separate classes with low density overlapped area
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn number of classes of input data Clustering with no priori knowledge Topology representation Realize real-time incremental learning Separate classes with low density overlapped area
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn number of classes of input data Clustering with no priori knowledge Topology representation Realize real-time incremental learning Separate classes with low density overlapped area
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn number of classes of input data Clustering with no priori knowledge Topology representation Realize real-time incremental learning Separate classes with low density overlapped area
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn number of classes of input data Clustering with no priori knowledge Topology representation Realize real-time incremental learning Separate classes with low density overlapped area
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn number of classes of input data Clustering with no priori knowledge Topology representation Realize real-time incremental learning Separate classes with low density overlapped area
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN for unsupervised learning: If two nodes connected with one path, the nodes belong to one class
1
Do SOINN for input data, output topology representation of nodes Initialize all nodes as unclassied. Randomly choose one unclassied node i from node set A. Mark node i as classied and label it as class Ci . Search A to nd all unclassied nodes that are connected to node i with a path. Mark these nodes as classied and label them as the same class as node i . Go to Step3 to continue the classication process until all nodes are classied.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
2 3
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN for unsupervised learning: If two nodes connected with one path, the nodes belong to one class
1
Do SOINN for input data, output topology representation of nodes Initialize all nodes as unclassied. Randomly choose one unclassied node i from node set A. Mark node i as classied and label it as class Ci . Search A to nd all unclassied nodes that are connected to node i with a path. Mark these nodes as classied and label them as the same class as node i . Go to Step3 to continue the classication process until all nodes are classied.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
2 3
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN for unsupervised learning: If two nodes connected with one path, the nodes belong to one class
1
Do SOINN for input data, output topology representation of nodes Initialize all nodes as unclassied. Randomly choose one unclassied node i from node set A. Mark node i as classied and label it as class Ci . Search A to nd all unclassied nodes that are connected to node i with a path. Mark these nodes as classied and label them as the same class as node i . Go to Step3 to continue the classication process until all nodes are classied.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
2 3
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN for unsupervised learning: If two nodes connected with one path, the nodes belong to one class
1
Do SOINN for input data, output topology representation of nodes Initialize all nodes as unclassied. Randomly choose one unclassied node i from node set A. Mark node i as classied and label it as class Ci . Search A to nd all unclassied nodes that are connected to node i with a path. Mark these nodes as classied and label them as the same class as node i . Go to Step3 to continue the classication process until all nodes are classied.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
2 3
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN for unsupervised learning: If two nodes connected with one path, the nodes belong to one class
1
Do SOINN for input data, output topology representation of nodes Initialize all nodes as unclassied. Randomly choose one unclassied node i from node set A. Mark node i as classied and label it as class Ci . Search A to nd all unclassied nodes that are connected to node i with a path. Mark these nodes as classied and label them as the same class as node i . Go to Step3 to continue the classication process until all nodes are classied.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
2 3
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN for unsupervised learning: If two nodes connected with one path, the nodes belong to one class
1
Do SOINN for input data, output topology representation of nodes Initialize all nodes as unclassied. Randomly choose one unclassied node i from node set A. Mark node i as classied and label it as class Ci . Search A to nd all unclassied nodes that are connected to node i with a path. Mark these nodes as classied and label them as the same class as node i . Go to Step3 to continue the classication process until all nodes are classied.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
2 3
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Conclusion of experiments Automatically reports number of classes. Perfectly clustering data with dierent shape and distribution. Find typical prototypes; incremental learning; de-noise; etc. its application F. Shen, O. Hasegawa Self-organizing incremental neural network and
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Conclusion of experiments Automatically reports number of classes. Perfectly clustering data with dierent shape and distribution. Find typical prototypes; incremental learning; de-noise; etc. its application F. Shen, O. Hasegawa Self-organizing incremental neural network and
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Conclusion of experiments Automatically reports number of classes. Perfectly clustering data with dierent shape and distribution. Find typical prototypes; incremental learning; de-noise; etc. its application F. Shen, O. Hasegawa Self-organizing incremental neural network and
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Conclusion of experiments Automatically reports number of classes. Perfectly clustering data with dierent shape and distribution. Find typical prototypes; incremental learning; de-noise; etc. its application F. Shen, O. Hasegawa Self-organizing incremental neural network and
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Conclusion of experiments Automatically reports number of classes. Perfectly clustering data with dierent shape and distribution. Find typical prototypes; incremental learning; de-noise; etc. its application F. Shen, O. Hasegawa Self-organizing incremental neural network and
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Conclusion of experiments Automatically reports number of classes. Perfectly clustering data with dierent shape and distribution. Find typical prototypes; incremental learning; de-noise; etc. its application F. Shen, O. Hasegawa Self-organizing incremental neural network and
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Experiment results Automatically reports there are 10 classes. Prototypes of every classes are reported. With such prototypes, recognition ratio (1-NN rule) is 90%.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Experiment results Automatically reports there are 10 classes. Prototypes of every classes are reported. With such prototypes, recognition ratio (1-NN rule) is 90%.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Experiment results Automatically reports there are 10 classes. Prototypes of every classes are reported. With such prototypes, recognition ratio (1-NN rule) is 90%.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Experiment results Automatically reports there are 10 classes. Prototypes of every classes are reported. With such prototypes, recognition ratio (1-NN rule) is 90%.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Experiment results Automatically reports there are 10 classes. Prototypes of every classes are reported. With such prototypes, recognition ratio (1-NN rule) is 90%.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn the number of prototypes needed to represent every class Only the prototypes used to determine the decision boundary will be remained Realize both types of incremental learning Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn the number of prototypes needed to represent every class Only the prototypes used to determine the decision boundary will be remained Realize both types of incremental learning Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn the number of prototypes needed to represent every class Only the prototypes used to determine the decision boundary will be remained Realize both types of incremental learning Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn the number of prototypes needed to represent every class Only the prototypes used to determine the decision boundary will be remained Realize both types of incremental learning Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Automatically learn the number of prototypes needed to represent every class Only the prototypes used to determine the decision boundary will be remained Realize both types of incremental learning Robust to noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN learns k for k-means. Noise-reduction removes noisy prototypes Center-cleaning removes prototypes unuseful for decision
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN learns k for k-means. Noise-reduction removes noisy prototypes Center-cleaning removes prototypes unuseful for decision
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN learns k for k-means. Noise-reduction removes noisy prototypes Center-cleaning removes prototypes unuseful for decision
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN learns k for k-means. Noise-reduction removes noisy prototypes Center-cleaning removes prototypes unuseful for decision
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Noise-reduction If the label of a node diers from the label of majority voting of its k-neighbors, it is considered an outlier. Center-cleaning If a prototype of class i has never been the nearest prototype of other classes, remove the prototype.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Noise-reduction If the label of a node diers from the label of majority voting of its k-neighbors, it is considered an outlier. Center-cleaning If a prototype of class i has never been the nearest prototype of other classes, remove the prototype.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Noise-reduction If the label of a node diers from the label of majority voting of its k-neighbors, it is considered an outlier. Center-cleaning If a prototype of class i has never been the nearest prototype of other classes, remove the prototype.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Noise-reduction If the label of a node diers from the label of majority voting of its k-neighbors, it is considered an outlier. Center-cleaning If a prototype of class i has never been the nearest prototype of other classes, remove the prototype.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Noise-reduction If the label of a node diers from the label of majority voting of its k-neighbors, it is considered an outlier. Center-cleaning If a prototype of class i has never been the nearest prototype of other classes, remove the prototype.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Compare with SVM and 1-NN LibSVM: 1197 support vectors; Recognition ratio = 96.6%. 1-NN: best classier (98%). All 3823 samples as prototypes.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Compare with SVM and 1-NN LibSVM: 1197 support vectors; Recognition ratio = 96.6%. 1-NN: best classier (98%). All 3823 samples as prototypes.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Compare with SVM and 1-NN LibSVM: 1197 support vectors; Recognition ratio = 96.6%. 1-NN: best classier (98%). All 3823 samples as prototypes.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Compare with SVM and 1-NN LibSVM: 1197 support vectors; Recognition ratio = 96.6%. 1-NN: best classier (98%). All 3823 samples as prototypes.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
KMC (M) 96.2 0.8 95.9 0.3 87.4 0.6 68.8 1.1 59.3 2.3 68.7 0.9 71.9 1.9 78.3 1.1
NNC (k) 96.7 0.6 97.0 0.2 86.1 0.7 72.3 1.2 67.3 1.6 74.7 0.7 73.9 1.9 81.1 0.99
LVQ (M) 96.1 0.6 96.3 0.4 86.4 0.8 68.3 2.0 66.3 1.9 73.5 0.9 72.3 1.5 79.9 1.2
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
KMC (M) 96.2 0.8 95.9 0.3 87.4 0.6 68.8 1.1 59.3 2.3 68.7 0.9 71.9 1.9 78.3 1.1
NNC (k) 96.7 0.6 97.0 0.2 86.1 0.7 72.3 1.2 67.3 1.6 74.7 0.7 73.9 1.9 81.1 0.99
LVQ (M) 96.1 0.6 96.3 0.4 86.4 0.8 68.3 2.0 66.3 1.9 73.5 0.9 72.3 1.5 79.9 1.2
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
NNC (k ) 100 (14) 100 (5) 100 (2) 100 (1) 100 (14) 100 (17) 100 (1) 100
LVQ (M ) 15 (22) 5.9 (40) 6.8 (24) 45 (97) 8.4 (29) 3.4 (26) 32 (57) 16.6
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
NNC (k ) 100 (14) 100 (5) 100 (2) 100 (1) 100 (14) 100 (17) 100 (1) 100
LVQ (M ) 15 (22) 5.9 (40) 6.8 (24) 45 (97) 8.4 (29) 3.4 (26) 32 (57) 16.6
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Labeled instances are dicult, expensive, or time consuming to obtain. How can a system use large amount of unlabeled data with limited labeled data to built good classiers? New data are continually added to an already huge database How can a system learn new knowledge without forgetting previous learned knowledge?
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Labeled instances are dicult, expensive, or time consuming to obtain. How can a system use large amount of unlabeled data with limited labeled data to built good classiers? New data are continually added to an already huge database How can a system learn new knowledge without forgetting previous learned knowledge?
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Labeled instances are dicult, expensive, or time consuming to obtain. How can a system use large amount of unlabeled data with limited labeled data to built good classiers? New data are continually added to an already huge database How can a system learn new knowledge without forgetting previous learned knowledge?
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Labeled instances are dicult, expensive, or time consuming to obtain. How can a system use large amount of unlabeled data with limited labeled data to built good classiers? New data are continually added to an already huge database How can a system learn new knowledge without forgetting previous learned knowledge?
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Labeled instances are dicult, expensive, or time consuming to obtain. How can a system use large amount of unlabeled data with limited labeled data to built good classiers? New data are continually added to an already huge database How can a system learn new knowledge without forgetting previous learned knowledge?
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN:represent topology, incremental learning; Labeled data: label nodes (winner); Division of a cluster
(11) (12)
dis(wa , wc )
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN:represent topology, incremental learning; Labeled data: label nodes (winner); Division of a cluster
(11) (12)
dis(wa , wc )
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN:represent topology, incremental learning; Labeled data: label nodes (winner); Division of a cluster
(11) (12)
dis(wa , wc )
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN:represent topology, incremental learning; Labeled data: label nodes (winner); Division of a cluster
(11) (12)
dis(wa , wc )
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
SOINN:represent topology, incremental learning; Labeled data: label nodes (winner); Division of a cluster
(11) (12)
dis(wa , wc )
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
5%, 15%, or 40% overlap training samples 500, validation samples 5,000, and test samples 5,000 labeled samples: 10% and 20% light blue: unlabeled data; others: labeled data - - - - - ideal decision boundary
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
5%, 15%, or 40% overlap training samples 500, validation samples 5,000, and test samples 5,000 labeled samples: 10% and 20% light blue: unlabeled data; others: labeled data - - - - - ideal decision boundary
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
5%, 15%, or 40% overlap training samples 500, validation samples 5,000, and test samples 5,000 labeled samples: 10% and 20% light blue: unlabeled data; others: labeled data - - - - - ideal decision boundary
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
5%, 15%, or 40% overlap training samples 500, validation samples 5,000, and test samples 5,000 labeled samples: 10% and 20% light blue: unlabeled data; others: labeled data - - - - - ideal decision boundary
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
5%, 15%, or 40% overlap training samples 500, validation samples 5,000, and test samples 5,000 labeled samples: 10% and 20% light blue: unlabeled data; others: labeled data - - - - - ideal decision boundary
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
5%, 15%, or 40% overlap training samples 500, validation samples 5,000, and test samples 5,000 labeled samples: 10% and 20% light blue: unlabeled data; others: labeled data - - - - - ideal decision boundary
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Experiment results
Separate classes with few labeled samples. For UCI data sets, work better than other typical methods.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Experiment results
Separate classes with few labeled samples. For UCI data sets, work better than other typical methods.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Experiment results
Separate classes with few labeled samples. For UCI data sets, work better than other typical methods.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Targets: Actively ask for label of some samples to label all classes Idea:
1 2 3 4
Use SOINN to learn the topology structure of input data. Actively label the vertex nodes of every class Use vertex nodes to label all nodes. Actively label the nodes lie in the overlapped area.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Targets: Actively ask for label of some samples to label all classes Idea:
1 2 3 4
Use SOINN to learn the topology structure of input data. Actively label the vertex nodes of every class Use vertex nodes to label all nodes. Actively label the nodes lie in the overlapped area.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Targets: Actively ask for label of some samples to label all classes Idea:
1 2 3 4
Use SOINN to learn the topology structure of input data. Actively label the vertex nodes of every class Use vertex nodes to label all nodes. Actively label the nodes lie in the overlapped area.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Targets: Actively ask for label of some samples to label all classes Idea:
1 2 3 4
Use SOINN to learn the topology structure of input data. Actively label the vertex nodes of every class Use vertex nodes to label all nodes. Actively label the nodes lie in the overlapped area.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Targets: Actively ask for label of some samples to label all classes Idea:
1 2 3 4
Use SOINN to learn the topology structure of input data. Actively label the vertex nodes of every class Use vertex nodes to label all nodes. Actively label the nodes lie in the overlapped area.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Targets: Actively ask for label of some samples to label all classes Idea:
1 2 3 4
Use SOINN to learn the topology structure of input data. Actively label the vertex nodes of every class Use vertex nodes to label all nodes. Actively label the nodes lie in the overlapped area.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Targets: Actively ask for label of some samples to label all classes Idea:
1 2 3 4
Use SOINN to learn the topology structure of input data. Actively label the vertex nodes of every class Use vertex nodes to label all nodes. Actively label the nodes lie in the overlapped area.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Original data: Four classes in all, with 10% noise. Results: under stationary environment; 10 teacher vectors.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Original data: Four classes in all, with 10% noise. Results: under stationary environment; 10 teacher vectors.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Original data: Four classes in all, with 10% noise. Results: under stationary environment; 10 teacher vectors.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
1 2
What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
4 5
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Diculties Forget previously learned knowledge when learning new knowledge incrementally. Storage limitation. Memory real-valued data. Many-to-Many associate.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Objectives of SOINN-AM
Incremental learning of memory pairs. Robust for noise data. Dealing with real-valued data. Many-to-many association.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Objectives of SOINN-AM
Incremental learning of memory pairs. Robust for noise data. Dealing with real-valued data. Many-to-many association.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Objectives of SOINN-AM
Incremental learning of memory pairs. Robust for noise data. Dealing with real-valued data. Many-to-many association.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Objectives of SOINN-AM
Incremental learning of memory pairs. Robust for noise data. Dealing with real-valued data. Many-to-many association.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Objectives of SOINN-AM
Incremental learning of memory pairs. Robust for noise data. Dealing with real-valued data. Many-to-many association.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Objectives of SOINN-AM
Incremental learning of memory pairs. Robust for noise data. Dealing with real-valued data. Many-to-many association.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Architecture of SOINN-AM
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Algorithms of SOINN-AM
Basic idea of memory phase
1 2
Combine key vector and associate vector as input data. Use SOINN to learn such input data.
Using key part of nodes to nd winner node for key vector, the distance is d. If d , output the associative part of winner as the recall results. If d > , report unknown for key vector.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Algorithms of SOINN-AM
Basic idea of memory phase
1 2
Combine key vector and associate vector as input data. Use SOINN to learn such input data.
Using key part of nodes to nd winner node for key vector, the distance is d. If d , output the associative part of winner as the recall results. If d > , report unknown for key vector.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Algorithms of SOINN-AM
Basic idea of memory phase
1 2
Combine key vector and associate vector as input data. Use SOINN to learn such input data.
Using key part of nodes to nd winner node for key vector, the distance is d. If d , output the associative part of winner as the recall results. If d > , report unknown for key vector.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Algorithms of SOINN-AM
Basic idea of memory phase
1 2
Combine key vector and associate vector as input data. Use SOINN to learn such input data.
Using key part of nodes to nd winner node for key vector, the distance is d. If d , output the associative part of winner as the recall results. If d > , report unknown for key vector.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Algorithms of SOINN-AM
Basic idea of memory phase
1 2
Combine key vector and associate vector as input data. Use SOINN to learn such input data.
Using key part of nodes to nd winner node for key vector, the distance is d. If d , output the associative part of winner as the recall results. If d > , report unknown for key vector.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Algorithms of SOINN-AM
Basic idea of memory phase
1 2
Combine key vector and associate vector as input data. Use SOINN to learn such input data.
Using key part of nodes to nd winner node for key vector, the distance is d. If d , output the associative part of winner as the recall results. If d > , report unknown for key vector.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Algorithms of SOINN-AM
Basic idea of memory phase
1 2
Combine key vector and associate vector as input data. Use SOINN to learn such input data.
Using key part of nodes to nd winner node for key vector, the distance is d. If d , output the associative part of winner as the recall results. If d > , report unknown for key vector.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Algorithms of SOINN-AM
Basic idea of memory phase
1 2
Combine key vector and associate vector as input data. Use SOINN to learn such input data.
Using key part of nodes to nd winner node for key vector, the distance is d. If d , output the associative part of winner as the recall results. If d > , report unknown for key vector.
F. Shen, O. Hasegawa Self-organizing incremental neural network and its application
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Original data
Binary data
Real-valued data
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Robustness of noise
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Input layer: key vector and associate vector. Memory layer: Memory patterns with classes. Associate layer: Build association between classes.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Input layer: key vector and associate vector. Memory layer: Memory patterns with classes. Associate layer: Build association between classes.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Input layer: key vector and associate vector. Memory layer: Memory patterns with classes. Associate layer: Build association between classes.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
Input layer: key vector and associate vector. Memory layer: Memory patterns with classes. Associate layer: Build association between classes.
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
1 2
What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
4 5
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa
Contents What is SOINN Why SOINN Detail algorithm of SOINN SOINN for machine learning SOINN for associative memory References
F. Shen, O. Hasegawa