Development and Convergence Analysis of Training Algorithms with Local Learning Rate Adaptation

Como, Italy July 24-July 27

DOI Bookmark:

http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.857808

IEEE-INNS-ENNS International Joint Co ...

	This Article
	PURCHASE ARTICLE: $19 PDF HTML IEEE Xplore Subscribers
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by G.D. Magoulas Articles by V.P. Plagianakos Articles by M.N. Vrahatis

	ASCII Text	x
	G.D. Magoulas, V.P. Plagianakos, M.N. Vrahatis, "Development and Convergence Analysis of Training Algorithms with Local Learning Rate Adaptation," Neural Networks, IEEE - INNS - ENNS International Joint Conference on, vol. 1, pp. 1021, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1, 2000.

	BibTex	x
	@article{ 10.1109/IJCNN.2000.857808, author = {G.D. Magoulas and V.P. Plagianakos and M.N. Vrahatis}, title = {Development and Convergence Analysis of Training Algorithms with Local Learning Rate Adaptation}, journal ={Neural Networks, IEEE - INNS - ENNS International Joint Conference on}, volume = {1}, year = {2000}, issn = {1098-7576}, pages = {1021}, doi = {http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.857808}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Neural Networks, IEEE - INNS - ENNS International Joint Conference on TI - Development and Convergence Analysis of Training Algorithms with Local Learning Rate Adaptation SN - 1098-7576 SP EP A1 - G.D. Magoulas, A1 - V.P. Plagianakos, A1 - M.N. Vrahatis, PY - 2000 KW - Globally convergent algorithms KW - local learning rate adaptation KW - batch training algorithms KW - gradient descent KW - feed-forward neural networks VL - 1 JA - Neural Networks, IEEE - INNS - ENNS International Joint Conference on ER -

G.D. Magoulas, University of Athens and University of Patras

V.P. Plagianakos, University of Patras

M.N. Vrahatis, University of Patras

A new theorem for the development and convergence analysis of supervised training algorithms with an adaptive learning rate for each weight is presented. Based on this theoretical result, a strategy is proposed to automatically adapt the search direction, as well as the step size length along the resultant search direction. This strategy is applied to some well-known local learning algorithms to investigate its effectiveness.

Index Terms:

Globally convergent algorithms, local learning rate adaptation, batch training algorithms, gradient descent, feed-forward neural networks

Citation:

G.D. Magoulas, V.P. Plagianakos, M.N. Vrahatis, "Development and Convergence Analysis of Training Algorithms with Local Learning Rate Adaptation," ijcnn, vol. 1, pp.1021, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1, 2000

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.