Professional Documents
Culture Documents
Neural Networks
Neural Networks
3
Biological Neuron
Neurons in the Brain
Brain is composed of neurons
neuron receives input from other neurons
from
its synapses
Axons connect to dendrites via synapses
• Summation functions
• Threshold activation function
McCulloch-Pitts Neuron Model
Architecture
The connected weight may be excitatory or inhibitory.
Excitatory +ive weights
inhibitory -ive weights
McCulloch-Pitts Neuron Model
Threshold is 2
McCulloch-Pitts Neuron Model
Threshold is 1
McCulloch-Pitts Neuron Model
McCulloch-Pitts Neuron Model
Types of learning
Supervised Learning
Unsupervised Learning
§ no teacher
§ expected output not known
§ system learns by itself
§ more complex
§ difficult to implement
§ self learning networks
Reinforcement Learning
Teacher is present
But no expected output
Indicates only the computed output correct or not
Reward for correct output and penalty for wrong output
Hebbian Learning
Two rules:
Hebbian Learning Contd…
Δb=y
Two cases:
1. If the product of input and output is +ive, increase in weight
2. If the product of input and output is -ive, decrease in weight
Hebbian Learning Contd…
Competitive Learning
§ when input is present all the neurons compete
§ winning neuron undergoes weight adjustment
§
Stochastic Learning
§ weights are adjusted in probabilistic fashion
§
The Perceptron
By Resenblatt in 1959
Initial proposal of connectionist networks
Computational model of the retina of the eye
Processing Elements in NN
An ANN consists of perceptrons. Each of the perceptrons receives
inputs, processes inputs and delivers a single output.
Perceptron
Summation Unit Thresholding Unit
x0=1
x1 w1
w0
w2
x2 o
.. n
I= wi xi
.
1 if I> θ
wn i=0 O=f(I)=
0 otherwise
xn
xi = input
wi =weight
O= Output
26
The Perceptron: Threshold
Activation Function
• Threshold activation function
1 if I>θ
O=f(I)=
0 otherwise
Linear Activation functions
• Output is scaled sum of inputs
N
y wn xn
n 1
Nonlinear Activation
Functions
• Sigmoid Neuron unit function
1
O f(I) I
1 e
Perceptron Contd...
Training: supervised learning
Computed output compared against target output
Weights are adjusted to minimize the error
T=Target Output
O= Perceptron Output
Class1 Class2
Exclusive Or (XOR) Problem
1 0
0
1
We could however construct multiple layers of perceptrons to get around this problem.
Single layer Perceptron
42