This document outlines the topics covered in a course on artificial neural networks (ANN). The course consists of 5 units that cover the basics of ANN including biological neural networks, feedforward and feedback networks, competitive learning networks, and applications of ANN such as pattern classification and speech recognition. The course uses a textbook on ANN and references additional books on neural networks, fuzzy logic, genetic algorithms, and artificial intelligence.
This document outlines the topics covered in a course on artificial neural networks (ANN). The course consists of 5 units that cover the basics of ANN including biological neural networks, feedforward and feedback networks, competitive learning networks, and applications of ANN such as pattern classification and speech recognition. The course uses a textbook on ANN and references additional books on neural networks, fuzzy logic, genetic algorithms, and artificial intelligence.
This document outlines the topics covered in a course on artificial neural networks (ANN). The course consists of 5 units that cover the basics of ANN including biological neural networks, feedforward and feedback networks, competitive learning networks, and applications of ANN such as pattern classification and speech recognition. The course uses a textbook on ANN and references additional books on neural networks, fuzzy logic, genetic algorithms, and artificial intelligence.
This document outlines the topics covered in a course on artificial neural networks (ANN). The course consists of 5 units that cover the basics of ANN including biological neural networks, feedforward and feedback networks, competitive learning networks, and applications of ANN such as pattern classification and speech recognition. The course uses a textbook on ANN and references additional books on neural networks, fuzzy logic, genetic algorithms, and artificial intelligence.
Introduction to ANN: Features, structure and working of Biological Neural Network
Trends in Computing Comparison of BNN and ANN. Basics of Artificial Neural Networks - History of neural network research, characteristics of neural networks terminology, models of neuron McCulloch - Pitts model, Perceptron, Ada line model, I Basic learning laws, Topology of neural network architecture 8 Back propagation networks : (BPN) Architecture of feed forward network, single layer ANN, multilayer perceptron, back propagation learning, input - hidden and output layer computation, back propagation algorithm, applications, selection of tuning II parameters in BPN, Numbers of hidden nodes, learning. 8 Activation & Synaptic Dynamics : Introduction, Activation Dynamics models, synaptic Dynamics models, stability and convergence, recall in neural networks. Basic functional units of ANN for pattern recognition tasks: Basic feed forward, Basic feedback and basic competitive learning neural network. Pattern association, III pattern classification and pattern mapping tasks. 8 a)Feedforward neural networks -- Linear responsibility X-OR problem and solution. - Analysis of pattern mapping networks summary of basic gradient search methods. b) Feedback neural networks Pattern Storage networks, stochastic networks and IV simulated annealing, Boltzmann machine and Boltzmann learning. 8 Competitive learning neural networks : Components of CL network pattern clustering and feature. Mapping network, ART networks, Features of ART models, character recognition using ART network. Applications of ANN: Pattern classification - Recognition of Olympic games symbols, Recognition of printed Characters. Neocognitron - Recognition of handwritten characters. NET Talk: to convert English text to speech. Recognition of consonant V vowel (CV) segments, texture classification and segmentation. 8
Text Book:
1. B. Yegnanarayana, "Artificial neural Networks", PHI Publication.
Reference Books: 1. S. Raj Sekaran ,VijayalakshmiPari," Neural networks, Fuzzy logic and Genetic Algorithms", PHI Publication. 2. Elaine Rich and Kevin Knight, "Artificial Intelligence", TMH Publication.