|
Title: Neural Networks
Accession Number: 01042142
Record Type: Component
Availability: Find a library where document is available Abstract: The resurgence of interest in neural networks (NNs) in the 1990s has been due mainly to the appearance of faster digital computers that can simulate large networks and the discovery of new NN architectures and more powerful learning mechanisms. The new NN architectures, for the most part, are not meant to duplicate the operation of the human brain, but rather to receive inspiration from known facts about how the brain works. This paper examines the multilayer perceptron architecture, other advanced topologies, the NN applications domain, strengths and weaknesses of NNs, and pitfalls to avoid.
Monograph Accession #: 01042139
Language: English
Authors: Ishak, SherifTrifiro, FrancoPagination: pp 17-32
Publication Date: 2007-1
Serial: Media Type: Web
Features: Figures
(8)
; References
TRT Terms: Subject Areas: Planning and Forecasting; Transportation (General); I72: Traffic and Transport Planning
Files: TRIS, TRB
Created Date: Feb 14 2007 6:48PM
More Articles from this Serial Issue: |