NNFL 2 - Guru Nanak Dev Engineering College

“Principles of Soft Computing, 2nd
Edition”
by S.N. Sivanandam & SN Deepa
Copyright © 2011 Wiley India Pvt. Ltd. All rights reserved.
CHAPTER 2
ARTIFICIAL NEURAL
NETWORKS: AN
INTRODUCTION

DEFINITION OF NEURAL NETWORKS
According to the DARPA Neural Network Study (1988,
AFCEA International Press, p. 60):
• ... a neural network is a system composed of many simple processing
elements operating in parallel whose function is determined by network
structure, connection strengths, and the processing performed at
computing elements or nodes.
According to Haykin (1994), p. 2:
A neural network is a massively parallel distributed processor that has
a natural propensity for storing experiential knowledge and making it
available for use. It resembles the brain in two respects:
•Knowledge is acquired by the network through a learning process.
•Interneuron connection strengths known as synaptic weights are used
to store the knowledge. “Principles of Soft Computing, 2nd
Edition”

BRAIN COMPUTATION
The human brain contains about 10 billion nerve cells, or
neurons. On average, each neuron is connected to other
neurons through approximately 10,000 synapses.
Edition”

INTERCONNECTIONS IN BRAIN
Edition”

BIOLOGICAL (MOTOR) NEURON
Edition”

 Information-processing system.
 Neurons process the information.
 The signals are transmitted by means of connection links.
 The links possess an associated weight.
 The output signal is obtained by applying activations to the net
input.
ARTIFICIAL NEURAL NET
Edition”

MOTIVATION FOR NEURAL NET
 Scientists are challenged to use machines more effectively for
tasks currently solved by humans.
 Symbolic rules don't reflect processes actually used by
humans.
 Traditional computing excels in many areas, but not in others.
Edition”

The major areas being:
 Massive parallelism
 Distributed representation and computation
 Learning ability
 Generalization ability
 Adaptivity
 Inherent contextual information processing
 Fault tolerance
 Low energy consumption.
Edition”

ARTIFICIAL NEURAL NET
X2
X1
W2
W1
Y
The figure shows a simple artificial neural net with two input neurons
(X1, X2) and one output neuron (Y). The inter connected weights are
given by W1 and W2.
Edition”

ASSOCIATION OF BIOLOGICAL NET
WITH ARTIFICIAL NET
Edition”

The neuron is the basic information processing unit of a NN. It consists
of:
1. A set of links, describing the neuron inputs, with weights W1, W2,
…, Wm.
2. An adder function (linear combiner) for computing the weighted sum
of the inputs (real numbers):
3. Activation function for limiting the amplitude of the neuron output.
j
j
jXWu
m
1
∑=
=
)(uy b+=ϕ
PROCESSING OF AN ARTIFICIAL NET
Edition”

BIAS OF AN ARTIFICIAL NEURON
The bias value is added to the weighted sum
∑wixi so that we can transform it from the origin.
Yin = ∑wixi + b, where b is the bias
x1-x2=0
x1-x2= 1
x1
x2
x1-x2= -1
Edition”

MULTI LAYER ARTIFICIAL NEURAL NET
INPUT: records without class attribute with normalized attributes
values.
INPUT VECTOR: X = { x1, x2, …, xn} where n is the number of
(non-class) attributes.
INPUT LAYER: there are as many nodes as non-class attributes,
i.e. as the length of the input vector.
HIDDEN LAYER: the number of nodes in the hidden layer and the
number of hidden layers depends on implementation.
Edition”

OPERATION OF A NEURAL NET
-
f
Weighted
sum
Input
vector x
Output y
Activation
function
Weight
vector w
∑
w0j
w1j
wnj
x0
x1
xn
Bias
Edition”

WEIGHT AND BIAS UPDATION
Per Sample Updating
•updating weights and biases after the presentation of each sample.
Per Training Set Updating (Epoch or Iteration)
•weight and bias increments could be accumulated in variables and
the weights and biases updated after all the samples of the training set
have been presented.
Edition”

STOPPING CONDITION
 All change in weights (∆wij) in the previous epoch are below some
threshold, or
 The percentage of samples misclassified in the previous epoch is
below some threshold, or
 A pre-specified number of epochs has expired.
 In practice, several hundreds of thousands of epochs may be
required before the weights will converge.
Edition”

BUILDING BLOCKS OF ARTIFICIAL NEURAL
NET
 Network Architecture (Connection between Neurons)
 Setting the Weights (Training)
 Activation Function
Edition”

Edition”

LAYER PROPERTIES
 Input Layer: Each input unit may be designated by an attribute
value possessed by the instance.
 Hidden Layer: Not directly observable, provides nonlinearities for
the network.
 Output Layer: Encodes possible values.
Edition”

TRAINING PROCESS
 Supervised Training - Providing the network with a series of
sample inputs and comparing the output with the expected
responses.
 Unsupervised Training - Most similar input vector is assigned
to the same output unit.
 Reinforcement Training - Right answer is not provided but
indication of whether ‘right’ or ‘wrong’ is provided.
Edition”

ACTIVATION FUNCTION
 ACTIVATION LEVEL – DISCRETE OR CONTINUOUS
 HARD LIMIT FUCNTION (DISCRETE)
• Binary Activation function
• Bipolar activation function
• Identity function
 SIGMOIDAL ACTIVATION FUNCTION (CONTINUOUS)
• Binary Sigmoidal activation function
• Bipolar Sigmoidal activation function
Edition”

ACTIVATION FUNCTION
Activation functions:
(A) Identity
(B) Binary step
(C) Bipolar step
(D) Binary sigmoidal
(E) Bipolar sigmoidal
(F) Ramp
Edition”

CONSTRUCTING ANN
 Determine the network properties:
• Network topology
• Types of connectivity
• Order of connections
• Weight range
 Determine the node properties:
• Activation range
 Determine the system dynamics
• Weight initialization scheme
• Activation – calculating formula
• Learning rule
Edition”

PROBLEM SOLVING
 Select a suitable NN model based on the nature of the problem.
 Construct a NN according to the characteristics of the application
domain.
 Train the neural network with the learning procedure of the
selected model.
 Use the trained network for making inference or solving problems.
Edition”

NEURAL NETWORKS
 Neural Network learns by adjusting the weights so as to be able
to correctly classify the training data and hence, after testing
phase, to classify unknown data.
 Neural Network needs long time for training.
 Neural Network has a high tolerance to noisy and incomplete
data.
Edition”

SALIENT FEATURES OF ANN
 Adaptive learning
 Self-organization
 Real-time operation
 Fault tolerance via redundant information coding
 Massive parallelism
 Learning and generalizing ability
 Distributed representation
Edition”

McCULLOCH–PITTS NEURON
 Neurons are sparsely and randomly connected
 Firing state is binary (1 = firing, 0 = not firing)
 All but one neuron are excitatory (tend to increase voltage of other
cells)
• One inhibitory neuron connects to all other neurons
• It functions to regulate network activity (prevent too many
firings)
Edition”

LINEAR SEPARABILITY
 Linear separability is the concept wherein the separation of the
input space into regions is based on whether the network response
is positive or negative.
 Consider a network having
positive response in the first
quadrant and negative response
in all other quadrants (AND
function) with either binary or
bipolar data, then the decision
line is drawn separating the
positive response region from
the negative response region.
Edition”

HEBB NETWORK
Donald Hebb stated in 1949 that in the brain, the learning is performed
by the change in the synaptic gap. Hebb explained it:
“When an axon of cell A is near enough to excite cell B, and repeatedly
or permanently takes place in firing it, some growth process or
metabolic change takes place in one or both the cells such that A’s
efficiency, as one of the cells firing B, is increased.”
Edition”

 The weights between neurons whose activities are positively
correlated are increased:
 Associative memory is produced automatically
 The Hebb rule can be used for pattern association, pattern
categorization, pattern classification and over a range of other
areas.
)x,x(ncorrelatio~
dt
dw
ji
ij
HEBB LEARNING
Edition”

FEW APPLICATIONS OF NEURAL
NETWORKS
Edition”

NNFL 2 - Guru Nanak Dev Engineering College

More Related Content

What's hot (20)

Similar to NNFL 2 - Guru Nanak Dev Engineering College (20)

Recently uploaded (20)

NNFL 2 - Guru Nanak Dev Engineering College