Scribd
Upload
61 views

EE7117

This document outlines the modules covered in the course EE7117 - Neural Networks offered by the Department of Electrical Engineering at BIRLA Institute of Technology, Ranchi, India. The 7 modules cover topics including: introduction to neural networks and their applications; supervised learning algorithms like perceptron and LMS; backpropagation for multilayer perceptrons; unsupervised learning techniques; associative models like Hopfield networks; and applications of neural networks in areas like character recognition and control systems. The document also lists two recommended text books and one reference book for the course.

Uploaded by

Vinayak Kumar
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
61 views

EE7117

This document outlines the modules covered in the course EE7117 - Neural Networks offered by the Department of Electrical Engineering at BIRLA Institute of Technology, Ranchi, India. The 7 modules cover topics including: introduction to neural networks and their applications; supervised learning algorithms like perceptron and LMS; backpropagation for multilayer perceptrons; unsupervised learning techniques; associative models like Hopfield networks; and applications of neural networks in areas like character recognition and control systems. The document also lists two recommended text books and one reference book for the course.

Uploaded by

Vinayak Kumar
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

BIRLA INSTITUTE OF TECHNOLOGY, RANCHI, INDIA

DEPARTMENT OF ELECTRICAL ENGINEERING



EE7117 NEURAL NETWORKS

Module - 1
Introduction - Brain & Machine, Biological Neurons & its mathematical model,
Artificial Neural Networks, Benefits and Applications, Architectures, Learning Process
(paradigms & algorithms), Correlation Matrix Memory, Adaptation. (6)
Module - 2
Supervised Learning I - Pattern space and Weight space, Linearly & non Linearly
separable classes, Decision Boundary, Hebbian learning & limitation, Perceptron,
Perceptron convergence theorem, Logic Functions implementations. (6)
Module - 3
LMS Algorithm: Wiener-Hopf equations, Steepest Descent Search method, LMS
algorithm, Convergence consideration in mean & mean square, Adaline, Learning curve,
Learning rate annealing schedules. (7)
Module - 4
Supervised Learning II: Multilayer Perceptrons, Backpropagation algorithm, XOR
Problem, Training modes, Optimum learning, Local minima, Network Pruning
techniques. (7)
Module - 5
Unsupervised Learning: Clustering, Hamming Networks, Maxnet, Simple competitive
learning,Winner-Take-All Networks, Learning Vector Quantizers, Counterpropagation
Networks, Self Organising Maps (Kohonen Networks), Adaptive Resonance Theory. (6)
Module - 6
Associative Models: Hopfield Networks (Discrete and continuous), Storage capacity,
Energy Function & minimization, Brain-State-in-a-Box Neural Network. (6)
Module - 7
Applications of ANN & Matlab Simulation: Character Recognition, Control
Applications, Data compression, Self organizing semantic Maps. (7)

Text Books:
1. Neural Networks : A Comprehensive Foundation Siman Haykin. (Pearson
Education)
2 Elements of Artificial Neural Networks Kishan Mehrotra, Chilukuri K. Mohan,
Sanjay Ranka. ( Penram International Publishing, India)

Reference Book
1. Neural Networks: A Classroom Approach Satish Kumar, Tata McGraw Hill)

You might also like