Error Estimation and Error Bounds for Neural Networks

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Hualou Liang Articles by Guiliang Dai

2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems (ANNES '95)

Dunedin, New Zealand

November 20-November 23

ISBN: 0-8186-7174-2

	ASCII Text	x
	Hualou Liang, Guiliang Dai, "Error Estimation and Error Bounds for Neural Networks," Artificial Neural Networks and Expert Systems, New Zealand Conference, pp. 42, 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems (ANNES '95), 1995.

	BibTex	x
	@article{ 10.1109/ANNES.1995.499435, author = {Hualou Liang and Guiliang Dai}, title = {Error Estimation and Error Bounds for Neural Networks}, journal ={Artificial Neural Networks and Expert Systems, New Zealand Conference}, volume = {0}, year = {1995}, isbn = {0-8186-7174-2}, pages = {42}, doi = {http://doi.ieeecomputersociety.org/10.1109/ANNES.1995.499435}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Artificial Neural Networks and Expert Systems, New Zealand Conference TI - Error Estimation and Error Bounds for Neural Networks SN - 0-8186-7174-2 SP EP A1 - Hualou Liang, A1 - Guiliang Dai, PY - 1995 KW - Neural network KW - Error estimation KW - Error bounds VL - 0 JA - Artificial Neural Networks and Expert Systems, New Zealand Conference ER -

Hualou Liang, Chinese Academy of Sciences

Guiliang Dai, Chinese Academy of Sciences

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ANNES.1995.499435

A method is proposed to estimate the standard error of predicted values in multilayer perceptron(MLP). It is based on likelihood theory. It holds for all feedforward networks, irrespective of the topology or the specific task at hand. In addition, the bounds on a neural network with perturbed weights and inputs is analytically derived. The bounds obtained are applicable to both digital and analog network implementations. By computer simulation, the validity of the proposed methods has been illustrated.

Index Terms:

Neural network, Error estimation, Error bounds

Citation:

Hualou Liang, Guiliang Dai, "Error Estimation and Error Bounds for Neural Networks," annes, pp.42, 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems (ANNES '95), 1995

Peer Review Notice | Give Us Feedback

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