Beruflich Dokumente
Kultur Dokumente
Applications
• Pattern recognition
• Function estimation
• Classification
• Nonlinear modeling Neural networks complement
other existing tools
• Prediction / Forecast
• Time series analysis
• Visualization
Artificial Neural Networks
Short history of neural network development
INPUT x1 x2 x3
“weights” wi
3
OUTPUT f ( x) = ∑ wi xi + θ
i =1
Perceptron Training (“Supervised Learning”)
Classification Task
2
µ
E[w ] = ∑ y − ∑ wi xi + θ
µ
µ i
∂E
∆wi = −η
∂wi w
optimum
µ µ Eo = 0
∆wi = η δ xi
Note: Θ is treated like a weight
learning rate
µ µ µ
δ = ytarget − yactual
Gradient Descent Learning
initial value
η0
ηt =
t
1+
r
degree of adaptation
(after r steps 50% reduction of η)
Gradient Descent Learning
∆wi (t ) = η δ xi + α ⋅ ∆wi (t − 1)
x1 x2 40
35
Input 30
25
w1 w2 Weights f(x) 20
15
10
Neuron (linear) 5
0
8
6
X2
4 10
8
2 2 6
r
y = f( x ) = ∑ wi xi + θ
4
0 2
0
X1
i =1
INPUT x1 x2 x3
w 1
act (ξ ) =
1 + e −ξ
Hidden Layer
“activation function”
v
OUTPUT
r HID IN
y = f( x ) = act ∑ vh act ∑ whi xhi + ϑh + θ
h =1 i =1
Universal function approximators!
hidden bias output bias
The Sigmoidal Activation Function
1.0
0.8
1 0.6
act ( x) =
1 + e−x 0.4
0.2
0.0
-6 -4 -2 0 2 4 6 x
x1 x2
W2,1
9
W1,1 W2,2
W1,2
6
Hidden (sigmoidal)
f( x)
V1 V2 3
10
Output (linear) 0
8 6
8
6
4
4 X1
2 2
X2 0 0
r HID IN
y = f( x ) = ∑ vh act ∑ whi xhi + ϑh + θ
h =1 i =1
Gradient Descent Learning
The Multi-Layer Network Error Function
2
µ
( )
E[w ] = ∑ y − act ∑ vh act ∑ whi xi + ϑh + θ
µ
µ h i
hidden neuron output
new old
v h =v h + ∆v
∂E
∆vh = −η Hidden-to-Output weights
∂vh
After presentation of a pattern µ
Hidden Output
∆vh = η δ H h
new old
w hi =whi + ∆w
∂E
∆whi = −η Input-to-Hidden weights
∂whi
After presentation of a pattern µ
Input variables
∆whi = η δ h xhi
Back-Propagation of Errors (“Backprop”) (3)
Validation data
Test data
Error
Training data
Training Time
“Forced Stop”
Mapping Chemical Space: “Drugs” and “Nondrugs”
0
0 1
Score
Nondrugs
14
12
10 Σ = 76% Σ = 24%
%
8
y = f(x) 6
Score 4
0
0 1
Score
“Drug-Likeness” ?
O
O HN N
NH2 N
H N
O H O O O
NH2 OH H H
N O
N N N N
S N O N O S O
O S H
N N O N
O
N O N
H S H
H H N
N
O
Xenical™ (Orlistat)
Score = 0.54
The Jury Decision Approach
Encoder Network
Training Mode
Pattern Pattern
vector vector
Mapping Mode
Pattern Factor 1
vector
Factor 2
Sequence Analysis by ANN
Residue encoding: “Unary” vectors
Score A 10000000000000000000
C 01000000000000000000
Output
D 00100000000000000000
E 00010000000000000000
F 00001000000000000000
Hidden G 00000100000000000000
H 00000010000000000000
I 00000001000000000000
Input
K 00000000100000000000
L 00000000010000000000
M R N L L V I …
M 00000000001000000000
N 00000000000100000000
b) “sliding window”
P 00000000000010000000
Q 00000000000001000000
R 00000000000000100000
S 00000000000000010000
T 00000000000000001000
V 00000000000000000100
W 00000000000000000010
Y 00000000000000000001
SignalP Output
Neural network tutorial
http://diwww.epfl.ch/mantra/tutorial/english/