DocumentCode
3347792
Title
Theory of Monte Carlo sampling-based Alopex algorithms for neural networks
Author
Chen, Zhe ; Haykin, Simon ; Becker, Suzanna
Author_Institution
Commun. Res. Lab., McMaster Univ., Hamilton, Ont., Canada
Volume
5
fYear
2004
fDate
17-21 May 2004
Abstract
We propose two novel Monte Carlo sampling-based Alopex (ALgorithm Of Pattern EXtraction) algorithms for training neural networks. The proposed algorithms naturally combine the sequential Monte Carlo estimation and Alopex-like procedure for gradient-free optimization, and the learning proceeds within the recursive Bayesian estimation framework. Experimental results on various problems show encouraging convergence results.
Keywords
Bayes methods; Monte Carlo methods; learning (artificial intelligence); neural nets; optimisation; recursive estimation; sampling methods; Bayesian estimation; algorithm of pattern extraction; gradient-free optimization; neural network training; recursive estimation; sampling-based Alopex algorithms; sequential Monte Carlo estimation; Bayesian methods; Convergence; Machine learning algorithms; Monte Carlo methods; Neural networks; Optimization methods; Recursive estimation; Sampling methods; Simulated annealing; Stochastic processes;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
ISSN
1520-6149
Print_ISBN
0-7803-8484-9
Type
conf
DOI
10.1109/ICASSP.2004.1327157
Filename
1327157
Link To Document