Document Detail


Learning polynomial feedforward neural networks by genetic programming and backpropagation.
MedLine Citation:
PMID:  18238017     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
This paper presents an approach to learning polynomial feedforward neural networks (PFNNs). The approach suggests, first, finding the polynomial network structure by means of a population-based search technique relying on the genetic programming paradigm, and second, further adjustment of the best discovered network weights by an especially derived backpropagation algorithm for higher order networks with polynomial activation functions. These two stages of the PFNN learning process enable us to identify networks with good training as well as generalization performance. Empirical results show that this approach finds PFNN which outperform considerably some previous constructive polynomial network algorithms on processing benchmark time series.
Authors:
N Y Nikolaev; H Iba
Related Documents :
11154967 - Architecture for networked electronic patient record systems.
20823327 - Dynamic deterministic effects propagation networks: learning signalling pathways from l...
18237987 - A neural-network packet switch controller: scalability, performance, and network optimi...
19090017 - A linear-time algorithm for predicting functional annotations from ppi networks.
474517 - Statistical principles underlying analytic goal-setting in clinical chemistry.
15609177 - Health-based risk adjustment improving the pharmacy-based cost group model to reduce ga...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  14     ISSN:  1045-9227     ISO Abbreviation:  IEEE Trans Neural Netw     Publication Date:  2003  
Date Detail:
Created Date:  2008-02-01     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:  337-50     Citation Subset:  -    
Affiliation:
Dept. of Math. and Comput. Sci., Univ. of London, UK.
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:  Training integrate-and-fire neurons with the Informax principle II.
Next Document:  Neural-network hybrid control for antilock braking systems.