Neural Network Ppt Presentation 312v40

NEURAL NETWORK BY… SIDDHARTH PATEL CLASS: IT-B (SEM: V) ENR.NO: 100530116032

CONTENTS

:

 Introduction

 Architecture  Human

and Artificial Neurones  Applications  Advantages  Disadvantages  Neural network in future  Conclusion

1. INTRODUCTION .

1.1 WHAT IS A NEURAL NETWORK? NN is an information processing paradigm .  The key element of this paradigm is the novel structure. 

1.2 WHY USE NEURAL NETWORKS? Adaptive learning.  Self-Organisation.  Real Time Operation. 

2. ARCHITECTURE .

2.1 FEED-FORWARD (ASSOCIATIVE) NETWORKS Allow signals to travel one way only; from input to output.  There is no .  It tend to be straight forward networks . 

2.2 (AUTO ASSOCIATIVE) NETWORKS Signals travelling in both directions.  It is dynamic.  Their 'state' is changing continuously.  It is very powerful. 

2.3 NETWORK LAYERS. I.

II.

III.

Input: represents the raw information. Hidden: determined by the activities of the input units . Output: depends on the activity of the hidden units.

3.HUMAN AND ARTIFICIAL NEURONES

3.1 HOW THE HUMAN BRAIN LEARNS? Neuron collects signals from others through a host called dendrites.  Neuron sends out spikes of electrical activity through a long, thin stand known as an axon.  A synapse converts the activity from the axon into electrical effects that excite activity from the axon in the connected neurones. 

Components of a neuron

The synapse

4.APPLICATIONS

4.1 NEURAL NETWORKS IN BUSINESS      

Sales forecasting Industrial process control Customer research Data validation Risk management Target marketing

4.2 NEURAL NETWORKS IN MEDICINE 

 

cardiograms CAT scans ultrasonic scans, etc…

4.3 NEURAL NETWORKS IN BUSINESS Marketing  Credit Evaluation  Stock Market 

 OTHER APPLICATIONS Character Recognition  Image Compression  Food Processing  Signature Analysis  Monitoring 

5.ADVANTAGES: Adapt to unknown situation.  Autonomous learning & generalization.  Robustness: fault tolerance due to network redundancy.  Noise tolerance  Ease of maintenance 

6.DISADVANTAGES: No exact.  Large complexity of the network structure.  NN needs training to operate.  Requires high processing time for large NN.  NN sometimes become unstable. 

7.NEURAL NETWORK

IN FUTURE

Robots that can see, feel, and predict the world around them.  Composition of music.  Handwritten documents to be automatically transformed into formatted word processing documents.  Self-diagnosis of medical problems using neural networks. 

8.CONCLUSION: 

Their ability to learn by example makes them very flexible and powerful. There is no need to devise an algorithm to perform a specific task. There is no need to understand the internal mechanisms of that task. They are also very well suited for real time systems.

THANK YOU…