NDLI: TREAT: a trust-region-based error-aggregated training algorithm for neural networks

Content Provider	IEEE Xplore Digital Library
Author	Yixin Chen Wilamowski, B.M.
Copyright Year	2002
Description	Author affiliation: Dept. of Comput. Sci. & Eng., Pennsylvania State Univ., University Park, PA, USA (Yixin Chen)
Abstract	A trust-region-based error-aggregated training algorithm (TREAT) for multi-layer feedforward neural networks is proposed. In the same spirit as that of the Levenberg-Marquardt (LM) method, the TREAT algorithm uses a different Hessian matrix approximation, which is based on the Jacobian matrix derived from aggregated errors. An aggregation scheme is discussed. It can greatly reduce the size of the matrix to be inverted in each training iteration and thereby lower the iterative computational cost. Compared with the LM method, the TREAT algorithm is computationally less intensive, and requires less memory. This is especially important for large sized neural networks where the LM algorithm becomes impractical.
Sponsorship	IEEE IEEE Neural Networks Soc. (NNS) Int. Neural Network Soc
Starting Page	1463
Ending Page	1468
File Size	613265
Page Count	6
File Format	PDF
ISBN	0780372786
ISSN	10987576
DOI	10.1109/IJCNN.2002.1007733
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2002-05-12
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Neural networks Convergence Backpropagation algorithms Multi-layer neural network Feedforward neural networks Iterative algorithms Jacobian matrices Optimization methods Approximation algorithms Computational efficiency
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Mr. Siddhartha Mukherjee siddhartha@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	ndl-support@iitkgp.ac.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Libarray of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

A stochastic backpropagation algorithm for training neural networks

A convergent neural network learning algorithm

Advanced neural-network training algorithm with reduced complexity based on Jacobian deficiency

Two highly efficient second-order algorithms for training feedforward networks

A New BP Algorithm with Adaptive Momentum for FNNs Training

Composite squared-error algorithm for training feedforward neural networks

A fast feedforward training algorithm using a modified form of the standard backpropagation algorithm

Exponentiated backpropagation algorithm for multilayer feedforward neural networks

Use of dynamic tunneling with backpropagation in training feedforward neural networks

TREAT: a trust-region-based error-aggregated training algorithm for neural networks

Similar Documents

A stochastic backpropagation algorithm for training neural networks

A convergent neural network learning algorithm

Advanced neural-network training algorithm with reduced complexity based on Jacobian deficiency

Two highly efficient second-order algorithms for training feedforward networks

A New BP Algorithm with Adaptive Momentum for FNNs Training

Composite squared-error algorithm for training feedforward neural networks

A fast feedforward training algorithm using a modified form of the standard backpropagation algorithm

Exponentiated backpropagation algorithm for multilayer feedforward neural networks

Use of dynamic tunneling with backpropagation in training feedforward neural networks

TREAT: a trust-region-based error-aggregated training algorithm for neural networks