NEURAL NETWORK FUNDAMENTALS WITH GRAPHS at Meripustak

NEURAL NETWORK FUNDAMENTALS WITH GRAPHS

Books from same Author: BOSE

Books from same Publisher: McGraw Hill

Related Category: Author List / Publisher List


  • Retail Price: ₹ 0/- [ 0% off ]

    Seller Price: ₹ 0/-

Sold By: Machwan

Offer 1: Get 0 % + Flat ₹ 50 discount on shopping of ₹ 1000 [Use Code: 0]

Offer 2: Get 0 % + Flat ₹ 50 discount on shopping of ₹ 1500 [Use Code: 0]

Offer 3: Get 0 % + Flat ₹ 50 discount on shopping of ₹ 5000 [Use Code: 0]

Free Shipping (for orders above ₹ 499) *T&C apply.

Out of Stock
General Information  
Author(s)BOSE
PublisherMcGraw Hill
ISBN9780074635292
BindingSoftbound
LanguageEnglish
Publish YearJanuary 2008

Description

McGraw Hill NEURAL NETWORK FUNDAMENTALS WITH GRAPHS by BOSE

This text presents neural network theory for diverse applications in a unified way, where the structure of artificial neural networks are characterized by distinguished classes of graphs. The book first provides a clear but concise exposition of neuroscience fundamentals, graph theory and alogorithms. It then moves to a detailed analysis of perceptron and lms-theory based neural networks, multilayer feedforward networks, and self-organizing competitive learning neural networks. The text culminates with a chapter on selected applications. Key features developing graphing theory fundamentals for the systematic generation and characterization of ANN structures, students are not as confused by the multitudinous ANN structures that are present because they are using generic graphs to classify all structures. The use of MATLAB Toolbox to solve design problems heightens student awareness of powerful and convenient software that can be applied to design. By using growth and shrinkage networks for the modeling for biological neural network characteristics, students learn that to train only for interconnection weights is not sufficient - the structure must also be trained. The inclusion of applications, exceptions, myths and false claims is important, as neurocomputing may not be successful in all applications, and the student needs to be aware of the potential and pitfalls of neuro as opposed to classical computing.