A pruning method for the recursive least squared algorithm

Neural Networks : the Official Journal of the International Neural Network Society
C S LeungL W Chan

Abstract

The recursive least squared (RLS) algorithm is an effective online training method for neural networks. However, its conjunctions with weight decay and pruning have not been well studied. This paper elucidates how generalization ability can be improved by selecting an appropriate initial value of the error covariance matrix in the RLS algorithm. Moreover, how the pruning of neural networks can be benefited by using the final value of the error covariance matrix will also be investigated. Our study found that the RLS algorithm is implicitly a weight decay method, where the weight decay effect is controlled by the initial value of the error covariance matrix; and that the inverse of the error covariance matrix is approximately equal to the Hessian matrix of the network being trained. We propose that neural networks are first trained by the RLS algorithm and then some unimportant weights are removed based on the approximate Hessian matrix. Simulation results show that our approach is an effective training and pruning method for neural networks.

References

Jan 11, 2001·Neural Networks : the Official Journal of the International Neural Network Society·H ParkK Fukumizu
Jan 1, 1997·IEEE Transactions on Neural Networks·C Chatterjee, V P Roychowdhury
Jan 1, 1994·IEEE Transactions on Neural Networks·J T ConnorL E Atlas
Jan 1, 1994·IEEE Transactions on Neural Networks·G V Puskorius, L A Feldkamp
Jan 1, 1993·IEEE Transactions on Neural Networks·R Reed

❮ Previous
Next ❯

Citations

Mar 12, 2003·Neural Networks : the Official Journal of the International Neural Network Society·Chi-Sing Leung, Lai-Wan Chan
Mar 15, 2003·International Journal of Neural Systems·Chi-Sing Leung, Ping-Man Lam
Mar 19, 2013·Neural Networks : the Official Journal of the International Neural Network Society·Hong-Gui HanJun-Fei Qiao
Aug 10, 2013·IEEE/ACM Transactions on Computational Biology and Bioinformatics·N MeskinA Datta
Jun 9, 2009·IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society·Md Monirul IslamKazuyuki Murase
Mar 11, 2006·IEEE Transactions on Neural Networks·Yong XuChi-Sing Leung
Feb 1, 2008·IEEE Transactions on Bio-medical Engineering·James McNames, Mateo Aboy
Nov 16, 2004·Neural Networks : the Official Journal of the International Neural Network Society·Gang LengThomas Martin McGinnity
May 19, 2009·IEEE Transactions on Neural Networks·M Bortman, M Aladjem
Feb 6, 2008·IEEE Transactions on Neural Networks·C S LeungL W Chan
Feb 18, 2011·IEEE Transactions on Bio-medical Engineering·Omid Sayadi, Mohammad B Shamsollahi

❮ Previous
Next ❯

Related Concepts

Trending Feeds

COVID-19

Coronaviruses encompass a large family of viruses that cause the common cold as well as more serious diseases, such as the ongoing outbreak of coronavirus disease 2019 (COVID-19; formally known as 2019-nCoV). Coronaviruses can spread from animals to humans; symptoms include fever, cough, shortness of breath, and breathing difficulties; in more severe cases, infection can lead to death. This feed covers recent research on COVID-19.

Blastomycosis

Blastomycosis fungal infections spread through inhaling Blastomyces dermatitidis spores. Discover the latest research on blastomycosis fungal infections here.

Nuclear Pore Complex in ALS/FTD

Alterations in nucleocytoplasmic transport, controlled by the nuclear pore complex, may be involved in the pathomechanism underlying multiple neurodegenerative diseases including Amyotrophic Lateral Sclerosis and Frontotemporal Dementia. Here is the latest research on the nuclear pore complex in ALS and FTD.

Applications of Molecular Barcoding

The concept of molecular barcoding is that each original DNA or RNA molecule is attached to a unique sequence barcode. Sequence reads having different barcodes represent different original molecules, while sequence reads having the same barcode are results of PCR duplication from one original molecule. Discover the latest research on molecular barcoding here.

Chronic Fatigue Syndrome

Chronic fatigue syndrome is a disease characterized by unexplained disabling fatigue; the pathology of which is incompletely understood. Discover the latest research on chronic fatigue syndrome here.

Evolution of Pluripotency

Pluripotency refers to the ability of a cell to develop into three primary germ cell layers of the embryo. This feed focuses on the mechanisms that underlie the evolution of pluripotency. Here is the latest research.

Position Effect Variegation

Position Effect Variagation occurs when a gene is inactivated due to its positioning near heterochromatic regions within a chromosome. Discover the latest research on Position Effect Variagation here.

STING Receptor Agonists

Stimulator of IFN genes (STING) are a group of transmembrane proteins that are involved in the induction of type I interferon that is important in the innate immune response. The stimulation of STING has been an active area of research in the treatment of cancer and infectious diseases. Here is the latest research on STING receptor agonists.

Microbicide

Microbicides are products that can be applied to vaginal or rectal mucosal surfaces with the goal of preventing, or at least significantly reducing, the transmission of sexually transmitted infections. Here is the latest research on microbicides.

Related Papers

IEEE Transactions on Neural Networks
C S LeungW K Kan
Neural Networks : the Official Journal of the International Neural Network Society
Chi-Sing Leung, L W Chan
IEEE Transactions on Neural Networks
Yong XuChi-Sing Leung
© 2021 Meta ULC. All rights reserved