Aravali college of Engineering and Management, Faridabad (13)

1
Program Name B.Tech CSE Course Name Machine
Learning NEURAL NETWORKS
2
CONTENTS

• Introduction.
• Artificial Neural Networks.
• Model of Artificial Neurons.
• Neural Network Architecture.
• Single Layer Feed Forward Networks.
• Learning of ANN.
• Applications of ANN.

3
INTRODUCTION

• Neural networks are the simplified models of
  the biological neuron systems.
• Neural networks are typically organized in
  layers. Layers are made up of a number of
  interconnected 'nodes' .which contain an
  'activation function'.
• Patterns are presented to the network via the
  'input layer', which communicates to one or more
  'hidden layers' where the actual processing is
  done via a system of weighted 'connections'.
• The hidden layers then link to an 'output layer'
  where the answer is output

4
ARTIFICIAL NEURAL NETWORKS
Output
Inputs
An artificial neural network is composed of many
artificial neurons that are linked together
according to a specific network architecture. The
objective of the neural network is to transform
the inputs into meaningful outputs.
5
MODEL OF ARTIFICIAL NEURON

• An appropriate model/simulation of the nervous
  system should be able to produce similar
  responses and behaviours in artificial systems.
• The nervous system is build by relatively simple
  units, the neurons, so
• copying their behaviour and functionality should
  be the solution.

6
MODEL OF ARTIFICIAL NEURON
Neuron consists of three basic components
weights, thresholds and a single activation
function A set or connection link each of which
is characterized by a weight or strength of its
own wkj. Specifically, a signal xj at the input
synapse j? connected to neuron k? is multiplied
by the synaptic wkj
An adder For summing the input signals, weighted
by respective synaptic strengths of the neuron
in a linear operation.
I w1x1
w2 x2 ....... wn xn wi xi
n
i 1
7
MODEL OF ARTIFICIAL NEURON
Threshold for a Neuron- The total input for each
neuron is the sum of the weighted inputs to the
neuron minus its threshold value. This is then
passed through the sigmoid function. The
equation for the transition in a neuron is a
1/(1 exp(- x)) where x ai wi - Q a is the
activation for the neuron ai is the activation
for neuron i wi is the weight Q is the
threshold subtracted
8
MODEL OF ARTIFICIAL NEURON

• Activation function An activation function f
  performs a mathematical operation on the signal
  output. The most common activation functions
  are
• - Linear Function,
• Threshold Function,
• Sigmoidal (S shaped) function,
• The activation functions are chosen depending
  upon the type of problem to be solved by the
  network.

9
MODEL OF ARTIFICIAL NEURON
Activation Functions f Types- Sigmoidal
Function (S-shape function)- The nonlinear
curved S-shape function is called the sigmoid
function. This is most common type of activation
used to construct the neural networks. It is
mathematically well behaved, differentiable and
strictly increasing function.
1
Y f (I)
,0 f (I ) 1
1 e 1/(1 exp( I )),0 f (I ) 1
I
This is explained as 0 for large -ve input
values, 1 for large ve values, with a smooth
transition between the two. a is slope parameter
also called shape parameter symbol the ? is also
used to represented this parameter.
10
NEURAL NETWORK ARCHITECTURE

• An artificial Neural Network is defined as a data
  processing system consisting of a large number
  of interconnected processing elements or
  artificial neurons.
• There are three fundamentally different classes
  of neural networks. Those are.
• Single layer feedforward Networks.
• Multilayer feedforward Networks.
• Recurrent Networks.
• Here we have to discuss the single layer feed
  forward network.

11
SINGLE-LAYER FEED FORWARD NETWORK
20 March 2013

• Input layer of source nodes that projects
  directly
• onto an output layer of neurons.
• Single-layer referring to the output layer of
  computation nodes (neuron).

12
SINGLE-LAYER FEED FORWARD NETWORK
Ii1 Ii2
Oi1 W11
1
Io1 W21
Yo1
1
Oi2
2
Yo2
Io2
2
Ii3
Oi3
W31
3
Iom
Yo m
Iin
3
Wn1
Oin
4

• The above figure is a single layer feed forward
  neural network. It consists an input layer to
  receive the inputs and an output layer to output
  the vectors.
• The input layer consists of n? neurons, and the
  output layer contains m?
• neurons .
• The weight of synapse connecting ith input
  neuron the jth output neuron is Wij.

13
SINGLE-LAYER FEED FORWARD NETWORK
Here the inputs of the input layer and the
outputs of the output layer is
given as
Ii1 I i 2 ..
Oo1 Oo 2 ..
O
I
o
1
Oom ......
Iin
m 1
n 1 W2 j II 2 Wnj IIN
So
Ioj W1 j I I1
Hence, the input to the output layer can be given
as
W T W T
O I
I
I I
o m 1 m n n 1
II
OI
Because
n 1 m 1
F(I,W)
I
O
The block diagram of a single layer feed forward
network.
14
LEARNING IN ANN

• Learning methods in neural networks can be
  broadly classified in three basic types.
• Supervised Learning
• Unsupervised Learning
• Reinforcement Learning
• Supervised Learning-

• In supervised learning, both the inputs and the
  outputs are provided. The network then processes
  the inputs and compares its resulting outputs
  against the desired outputs
• Errors are then calculated, causing the system to
  adjust the weights which control the network.
• Here a teacher is assume to be present during the
  learning process.

?
15
LEARNING IN ANN

• Unsupervised Learning-
• Here the target output is not presented to the
  network, Because there
• is no teacher to present the described patterns.
• So the system learns of its own by discovering
  and adapting to structural features of the input
  patterns.
• Reinforcement Learning-
• In this method, a teacher though available,
  does not present the expected answer but
  only indicates if the computed output is correct
  or incorrect.
• The information provided helps the network in its
  learning process.
• Here a reward is given for correct answer
  computed and a penalty for a wrong answer.

16
APPLICATIONS OF NEURAL NETWORKS

• Character Recognition- Neural networks can be
  used to recognize handwritten characters.
• Image Compression- Neural networks can receive
  and process vast amounts of information at once,
  making them useful in image compression.
• Stock Market Prediction- Neural networks can
  examine a lot of information quickly and sort it
  all out, they can be used to predict stock
  prices.
• Travelling Salesman Problem- Neural networks can
  solve the traveling salesman problem, but only
  to a certain degree of approximation.
• Security and Loan Applications- With the
  acceptation of a neural network that will decide
  whether or not to grant a loan.

17

Aravali College of Engineering And
Management Jasana, Tigoan Road, Neharpar,
Faridabad, Delhi NCR Toll Free Number 91-
8527538785 Website  www.acem.edu.in