Document Detail


Neural network learning without backpropagation.
MedLine Citation:
PMID:  20858577     Owner:  NLM     Status:  In-Process    
Abstract/OtherAbstract:
The method introduced in this paper allows for training arbitrarily connected neural networks, therefore, more powerful neural network architectures with connections across layers can be efficiently trained. The proposed method also simplifies neural network training, by using the forward-only computation instead of the traditionally used forward and backward computation.
Authors:
Bogdan M Wilamowski; Hao Yu
Related Documents :
7740247 - Exercise programmes in the treatment of children with learning disabilities.
15215077 - Methods in the study of motor programming: is it just a matter of simple vs. choice rea...
22084997 - Interactive lecturing.
16235127 - Characterizing the learning curve for a basic laparoscopic drill.
18669877 - Adhd symptomatology and its relationship to factors associated with college adjustment.
200747 - A collaborative model for university nursing education and agency staff development.
Publication Detail:
Type:  Journal Article     Date:  2010-09-20
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  21     ISSN:  1941-0093     ISO Abbreviation:  IEEE Trans Neural Netw     Publication Date:  2010 Nov 
Date Detail:
Created Date:  2010-11-04     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101211035     Medline TA:  IEEE Trans Neural Netw     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1793-803     Citation Subset:  IM    
Affiliation:
Department of Electrical and Computer Engineering, Auburn University, Auburn, AL 36849-5201 USA. wilam@ieee.org
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Approximation-based adaptive tracking control of pure-feedback nonlinear systems with multiple unkno...
Next Document:  High-performance reconfigurable hardware architecture for restricted Boltzmann machines.