Paper Info
Title
On the application of orthogonal transformation for the design and analysis of feedforward networks.
Abstract
Orthogonal transformation, which can lead to compaction of information, has been used in two ways to optimize on the size of feedforward networks: 1) through the selection of optimum set of time-domain inputs, and the optimum set of links and nodes within a neural network (NN); and 2) through the orthogonalization of the data to be used in NN's, in case of processes with periodicity. The proposed methods are efficient and are also extremely robust numerically. The singular value decomposition (SVD) and QR with column pivoting factorization (QRcp) are the transformations used. SVD mainly serves as the null space detector; QRcp coupled with SVD is used for subset selection, which is one of the main operations on which the design of the optimal network is based. SVD has also been used to devise a new approach for the assessment of the convergence of the NN's, which is an alternative to the conventional output error analysis.
Year
DOI
Venue
1995
10.1109/72.410351
IEEE Transactions on Neural Networks
Keywords
Field
DocType
convergence of numerical methods,feedforward neural nets,optimisation,singular value decomposition,time-domain analysis,transforms,column pivoting factorization,convergence,feedforward networks,neural network,null space detector,orthogonal transformation,singular value decomposition,time-domain inputs
Kernel (linear algebra),Convergence (routing),Singular value decomposition,Mathematical optimization,Orthogonal transformation,Computer science,Factorization,Artificial intelligence,Artificial neural network,Orthogonalization,Machine learning,Feed forward
Journal
Volume
Issue
ISSN
6
5
1045-9227
Citations 
PageRank 
References 
26
2.60
6
Authors
2
Name
Order
Citations
PageRank
P P Kanjilal16619.54
D N Banerjee2262.60