Neural Networks by kWC8nQlW

VIEWS: 1 PAGES: 18

									    A Seminar
On Neural Networks




   www.wittyengineers.com
             CONTENTS

1. Introduction to Neural Netwoks
2. Human and Artificial Neurones -
   investigating the similarities
3. An Engineering approach
4. Architecture of neural networks
5. Applications of neural networks
6. Conclusion
            Introduction
● What Is Neural Network?

An Artificial Neural Network (ANN) is an
information processing paradigm that is
inspired by the way biological nervous
systems, such as the brain, process
information.
● Why Use Neural Networks?
 A trained neural network can be thought of as an
 "expert" in the category of information it has been given
 to analyze.

 The Other advantages include:
 1.Adaptive learning
 2.Self-Organisation
 3.Real Time Operation
 4.Fault Tolerance via Redundant Information Coding
● Neural Networks Vs
  Conventional Computers
 1.Conventional computers use an algorithmic
 approach i.e. the computer follows a set of
 instructions in order to solve a problem .

 2. The network is composed of a large number
 of highly interconnected processing elements
 (neurones) working in parallel to solve a specific
 problem. Neural networks learn by example.
        Human and
         Artificial
  Neurones - Investigating
           The

                 Similarities
● How the Human Brain
 Learns?
  An Engineering
  Approach
● A Simple Neuron:
Firing Rules
Before Firing:




After Firing:
Example



 ● If we represent black squares with 0 and white squares with 1 then the
   truth tables for the 3 neurones after generalisation are


Top Neuron
Middle Neuron




Bottom Neuron
A More Complicated Neuron




       An MCP Neuron
Architecture Of Neural
Networks
● Feed-forward networks
Feedback networks
              Network Layers
● INPUT: The activity of the input units represents the
 raw information that is fed into the network.

● HIDDEN: The activity of each hidden unit is determined
 by the activities of the input units and the weights on the
 connections between the input and the hidden units.

● OUTPUT: The behaviour of the output units depends
 on the activity of the hidden units and the weights
 between the hidden and output units.
Perceptrons
Applications of neural
networks
1. Neural networks in medicine
      ■ Electronic noses
      ■ Instant Physician
2. Neural Networks in business
     ■ sales forecasting
     ■ industrial process control
     ■ customer research
     ■ data validation
     ■ risk management
     ■ target marketing
Thanks

								
To top