Sie sind auf Seite 1von 27

Artificial Neuron Network

An idea

Since ancient times. ; this field was established before the advent of computers,

The first artificial neuron was produced in 1943 by the neurophysiologist Warren McCulloch and the logician Walter Pits
But not realm

Conventional computing versus artificial neural networks


Traditional computers: processing is sequential, function logically with a set of rules and calculations, must learn only by doing different sequences or steps in an algorithm, top-down learning.
An ANN: is an inherently multiprocessor, can function via images, pictures, and concepts, neural networks can program themselves, Bottom-up learning.

Getting familiar to ANN

Model of ANN

Rules for the operation of the neurons


1.

Propagation delay is assumed to be constant for all neurons, Neurons fire at discrete moments, not continuously. Each synapse output stage impinges onto only one synaptic input stage on a subsequent neuron. Each neuron can have a number of input synaptic stages. Synaptic input stages contribute to overcoming of a threshold below which the neuron will not fire.

2. 3.

4.

5.

Firing rules

X1: 0 X2: 0 X3: 0 OUT: 0

0 0 1 0

0 0 1 1 0 1 0/1 0/1

1 0 0 0/1

1 0 1 1

1 1 1 1 0 1 0/1 1

The perceptron

The perceptron is a mathematical model of a


biological neuron.

a perceptron calculates the weighted sum of the input values. the perceptron outputs a non-zero value only when the weighted sum exceeds a certain threshold. Output of P = {1 if A x + B y > C
{0 if A x + B y < = C

Architecture of Neural Networks


Competitive neural networks Feed-forward networks Feed-back networks

Simple competitive networks:

Composed of

The Hemming net

The Maxnet

Each perceptron at the top layer of the Hemming net calculates a weighted sum of the input values. This weighted sum can be interpreted as the dot product of the input vector and the weight vector.
The maxnet is a fully connected network with each node connecting to every other nodes, including itself. The basic idea is that the nodes compete against each other by sending out inhibiting signals to each other.

In a simple competitive network, a Maxnet connects the top nodes of the Hemming net.
Whenever an input is presented, the Hemming net finds out the distance of the weight vector of each node from the input vector via the dot product, while the Maxnet selects the node with the greatest dot product. In this way, the whole network selects the node with its weight vector closest to the input vector, i.e. the winner.

Feed-Forward networks

Feed-forward networks characteristics

1. Perceptrons are arranged in layers, with the first layer taking in inputs and the last layer producing outputs. The middle layers have no connection with the external world, and hence are called hidden layers.
2. Each perceptron in one layer is connected to every perceptron on the next layer. Hence information is constantly "fed forward" from one layer to the next., and this explains why these networks are called feed-forward networks. 3. There is no connection among perceptrons in the same layer.

feed-forward networks are commonly used for


classification.

Back-propagation -- learning in feed-forward networks

pairs of input and output values are fed into the network for many cycles, so that the network 'learns' the relationship between the input and output.
{

i i i i i i

= = = = = =

(1, 2) (1, 3) (2, 3) (3, 4) (5, 6) (6, 7)

, , , , , ,

o o o o o o

=( 0, 0) = (0, 0) = (1, 0) = (1, 0) = (0, 1) = (0, 1)

BACK-PROPAGATION FORMULAE

Feedback networks

The Learning Process

Associative mapping
Auto-association Hetero-association

Regularity detection

Supervised learning Unsupervised learning

Transfer/Activation Function

The Activation Function accepts a value that is the weighted sum of neuron inputs and returns a value that represents the output of the neuron.
This function should be used for training neural networks because a continuous function like this gives better feedback about the degree of error in a network.

To make a neural network that performs some specific task, we must set the weights on the connections appropriately.

Sigmoid Function

Some specific details of neural networks

Classification. (pattern recognition programs ) Prediction. (stock market prediction) Clustering. (data-mining ) Association. ("remember" )

Applications of neural networks

Sales forecasting. Industrial process control. Data validation. Target marketing. Recognition of speakers in communications. Diagnosis of hepatitis. Recovery of telecommunications from faulty software. Facial recognition

Conclusion

The computing world has a lot to gain from neural networks. Neural networks have a huge potential we will only get the best of them when they are integrated with computing, AI, fuzzy logic and related subjects.

Das könnte Ihnen auch gefallen