Document Detail

Iterative fast orthogonal search algorithm for MDL-based training of generalized single-layer networks.
MedLine Citation:
PMID:  11152209     Owner:  NLM     Status:  MEDLINE    
The generalized single-layer network (GSLN) architecture, which implements a sum of arbitrary basis functions defined on its inputs, is potentially a flexible and efficient structure for approximating arbitrary nonlinear functions. A drawback of GSLNs is that a large number of weights and basis functions may be required to provide satisfactory approximations. In this paper, we present a new approach in which an algorithm known as iterative fast orthogonal search (IFOS) is coupled with the minimum description length (MDL) criterion to provide automatic structure selection and parameter estimation for GSLNs. The resulting algorithm, dubbed IFOS-MDL, performs both network growth and pruning to construct sparse GSLNs from potentially large spaces of candidate basis functions.
K M Adeney; M J Korenberg
Related Documents :
19453619 - Food web models: a plea for groups.
7213909 - Contact networks and the study of contagion.
1593899 - Propagation of information in metanet graph models.
15855409 - Bayesian network analysis of signaling networks: a primer.
19348639 - A network inference workflow applied to virulence-related processes in salmonella typhi...
15112369 - Predicting spatial data with rbf networks.
23700999 - Evolutionary computation and qsar research.
23056379 - Calcification, storm damage and population resilience of tabular corals under climate c...
9579809 - Solution conformation and dynamics of a fungal cell wall polysaccharide isolated from m...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Neural networks : the official journal of the International Neural Network Society     Volume:  13     ISSN:  0893-6080     ISO Abbreviation:  Neural Netw     Publication Date:  2000 Sep 
Date Detail:
Created Date:  2001-01-09     Completed Date:  2001-02-15     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  8805018     Medline TA:  Neural Netw     Country:  United States    
Other Details:
Languages:  eng     Pagination:  787-99     Citation Subset:  IM    
Department of Electrical and Computer Engineering, Queen's University, Kingston, Ontario, Canada.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Neural Networks (Computer)*

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

Previous Document:  Multi-step-ahead prediction using dynamic recurrent neural networks.
Next Document:  Approximating a solution of the s-t max-cut problem with a deterministic annealing algorithm.