neural

21
NEURAL NETWORK & THEIR APPLICATIONS BY DAKSHIMA SHARMA COMPUTER SCIENCE ENGINEERING 3 RD YEAR

Upload: archit-rastogi

Post on 11-May-2015

2.335 views

Category:

Documents


2 download

DESCRIPTION

neural networks basics

TRANSCRIPT

Page 1: Neural

NEURAL NETWORK & THEIR APPLICATIONS

BY DAKSHIMA SHARMACOMPUTER SCIENCE

ENGINEERING3RD YEAR

Page 2: Neural

INTRODUCTION• Models of the brain and nervous system• Process information much more like the brain than a

serial computer• Very simple principles and complex behaviours.• An Artificial Neural Network (ANN) is an information

processing paradigm that is inspired by biological nervous systems.

• It is composed of a large number of highly interconnected processing elements called neurons.

• An ANN is configured for a specific application, such as pattern recognition or data classification

Page 3: Neural

NEURAL SYSTEMBIOLOGICAL ARTIFICIAL

• They are made up of real biological neurons that are connected or functionally related in a nervous system .

• In the field of neuroscience, they are often identified as groups of neurons that perform a specific physiological function in laboratory analysis.

• They are composed of interconnecting artificial neurons (programming constructs that mimic the properties of biological neurons) for solving artificial intelligence problems without creating model of real system.

• The algorithms abstract away the biological complexity by focusing on the most important information. The goal of artificial neural networks human-like, predictive ability.

Page 4: Neural

WHY TO USE ANN???•ability to derive meaning from complicated

or imprecise data•extract patterns and detect trends that are

too complex to be noticed by either humans or other computer techniques

•Adaptive learning•Real Time Operation•Conventional computers use an algorithmic

approach, but neural networks works similar to human brain and learns by example.

Page 5: Neural

ARTIFICIAL NEURAL NETWORKS(ANN)-:• Also called simulated neural network (SNN), is an

interconnected group of natural or artificial neurons that uses a mathematical or computational model for information processing based on a connectionistic approach to computation.

• In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network.

• ANNs incorporate the two fundamental components of biological neural nets:

1. Neurones (nodes)

2. Synapses (weights)

Page 6: Neural

Analogy between ANN and NNN NODE V/S NEURON & WEIGHT V/S SYNAPSE

Page 7: Neural

BASICS OF NEURAL SYSTEM

1 A set of synapses or connecting links, each link characterized by a weight: W1, W2, …, Wm

2 An adder function (linear combiner) which computes the weighted sum of the inputs:

3 Activation function (squashing function) for limiting the amplitude of the output of the neuron.

m

1jj xwu

j

)(u y b

Page 8: Neural

ARCHITECTURE OF NEURAL SYSTEM

FEED FORWARD :

Neurons are arranged in acyclic layer and this arrangement can be of:

2)- Multilayer

Input layerof

source nodes

Output layer

ofneuro

ns

1)- Single layerInputlayer

Outputlayer

Hidden Layer

3-4-2 Network

Page 9: Neural

FEED FORWARD ANN• Information flow is

unidirectional

▫ Data is presented to I nput layer

▫ Passed on to Hidden Layer

▫ Passed on to Output layer

• Information is distributed

• Information processing is parallel

Page 10: Neural

RECURRENT ANN

▫ Nodes connect back to other nodes or themselves

▫ Information flow is multidirectional

▫ Sense of time and memory of previous state(s)

unit delay operator z-

1 implies dynamic system

• z-1

• z-1

• z-1

BLUE-inputBROWN-hiddenGREEN-output

Page 11: Neural

APPLICATIONS FINGERPRINT RECOGNITION

• Image Acquisition: the acquired image is digitalized into 512x512 image with each pixel assigned a particular gray scale value (raster image).

• Edge Detection and Thinning: these are preprocessing of the image , remove noise and enhance the image.

• Image acquisition

• edge detection

• Thining

• Feature extraction

• classification

• Ridge extraction

Page 12: Neural

FINGERPRINT RECOGNITION SYSTEM

• Feature extraction: this the step where we point out the features such as ridge bifurcation and ridge endings of the finger print with the help of neural network.

• Classification: here a class label is assigned to the image depending on the extracted features.

Page 13: Neural

PREPROCESSING SYSTEM The first phase is to capture a image The image is captured using TIR . The image is stored as a two

dimensional array of 512x512 size, each element of array representing a pixel and assigned a gray scale value from 256 gray scale levels.

Image is captured ,noise is removed using.

Edge detection: the edge is defined where the gray scale levels changes greatly. also, orientation of ridges is determined for each 32x32 block of pixels using gray scale gradient.

Ridge extraction: are extracted using the fact that gray scale value of pixels are maximum along the direction normal to the ridge orientation.

Page 14: Neural

PREPROCESSING SYSTEM Thinning: the extracted ridges are

converted into skeletal structure in which ridges are only one pixel wide. thinning should not-

Remove isolated as well as surrounded pixel.

Break connectedness. Make the image shorter.

• Multilayer perceptron network of three layers is trained to detect minutiae in the thinned image.

The first layer has nine perceptrons

The hidden layer has five perceptrons

The output layer has one perceptron.

The network is trained to output ‘1’ when the input window is centered at the minutiae and it outputs ‘0’ when minutiae are not present.

Page 15: Neural

FEATURE EXTRACTION

• Trained neural networks are used to analyze the image by scanning the image with a 3x3 window.

• To avoid falsely reported features which are due to noise –

The size of scanning window is increased to 5x5

If the minutiae are too close to each other than we ignore all of them.

Page 16: Neural

FACE RECOGNITION

90% accurate learning head pose, and recognizing 1-of-20 faces

Page 17: Neural

HANDWRITTEN DIGIT RECOGNITION

Page 18: Neural

OTHER APPLICATIONS Character Recognition - The idea of character

recognition has become very important as handheld devices like the Palm Pilot are becoming increasingly popular. 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. With the Internet explosion and more sites using more images on their sites, using neural networks for image compression is worth a look.

Page 19: Neural

OTHER APPLICATIONSStock Market Prediction - The day-to-day business of the stock market is extremely complicated. Many factors weigh in whether a given stock will go up or down on any given day. Since 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- Interestingly enough, neural networks can solve the travelling salesman problem, but only to a certain degree of approximation.

Medicine, Electronic Nose, Security, and Loan Applications - These are some applications that are in their proof-of-concept stage, with the acceptance of a neural network that will decide whether or not to grant a loan, something that has already been used more successfully than many humans.

Miscellaneous Applications - These are some very interesting (albeit at times a little absurd) applications of neural networks.

Page 20: Neural

SUMMARY• Neural network solutions should be kept as simple as

possible.

• For the sake of the gaming speed neural networks should be applied preferably off-line.

• A large data set should be collected and it should be divided into training, validation, and testing data.

• Neural networks fit as solutions of complex problems.

• A pool of candidate solutions should be generated, and the best candidate solution should be selected using the validation data.

• The solution should be represented to allow fast application.

Page 21: Neural

THE END..

DAKSHIMA SHARMA

SIGNING OFF…..