Alumni Career Download Contact UsInquiry Now

Artificial Neural Network

Dr. Medha Patel

High speed parallel processing and vector processing units with RISC concepts can truly reflect infrastructure of human brain. If the working methodology of human brain i.e. learning through examples, observing and analyzing for meaningful annotation from data is also simulated by software in computer technology, it can be a powerful tool to manage complex data with high speed and greater accuracy. ANNs are such tools with the ability to handle complex, nonlinear, sequential, high dimensional nonparametric data with the basic capability to learn patterns from examples. Artificial Neural Network (ANN)is an information processing system that has been developed as a generalization of the mathematical model of human cognition (ability to know). It consists of simple computational units called neurons that are highly interconnected and each connection has a strength that is expressed by a positive or negative number called weight. The connection of neurons is normally arranged in layers and executed in parallel. The connections are categorized as network topology. The size of the weight controls the influence that one neuron has on the other, with a positive weight excite an element and negative weight inhibit. Over all the activation of an element is determined by a combination (summation) of excitatory and inhibitory influence it receives from its neighbors. The weights of the net are adaptable which store the experimental knowledge from task example through a process of learning. Learning is the adaptive process simulated to human brain’s neural structure and overall architecture (cognition). The information is stored in the connections and distributed throughout, so the network can function as a memory of brain. The memory is content addressable, in the sense that the information may be recalled by providing partial or even erroneous input pattern. The information is stored in association of other stored data; hence it is adaptable. We try to use this algorithms for various applications like Genome sequence analysis, Image processing etc.

Institute Of Advanced Research
Koba Institutional Area, Gandhinagar, Gujarat - India, 382 007

Phone 079-30514100

Copyright © , All rights reserved.
Powered by : Adit Microsys