Neural nets : classical results and current problems

Technical Report

Público Deposited

Baixar PDF

Citeable URL: https://ir.library.oregonstate.edu/concern/technical_reports/1z40kv196

Descriptions

Attribute Name	Values
Creator	Oregon State University. Dept. of Computer Science Cull, Paul, 1943-
Abstract	This note briefly discusses some of the classical results of McCulloch and Pitts. It then deals with some current research in neural nets. Several questions about neural nets are shown to be computationally difficult by showing that they are NP-Complete or worse. The size of neural nets necessary to compute functions or simulate machines is discussed, and some worst case optimal results are given. The statistics of randomly chosen autonomous nets are discussed, together with some approaches to understanding these statistics. Recent results on the behavior of analog nets are discussed, and the possibility of silicon implementation is mentioned.
Resource Type	Research Paper
Date Available	2012-04-18T17:23:22+00:00
Date Issued	1995-04
Series	Technical report (Oregon State University. Department of Computer Science)
Subject	Neural networks (Computer science)
Declaração de direitos	Copyright Not Evaluated
Publisher	Corvallis, OR : Oregon State University, Dept. of Computer Science
Peer Reviewed	No
Language	English [eng]
Replaces	http://hdl.handle.net/1957/28802

Miniatura	Título	Data de carga	Acesso	Ações
	Neural_nets_classical_results_and_current_problems.pdf	2017-07-18	Público	Baixar