论文信息 - Implementation of the SANS algorithm on the CM2

Implementation of the SANS algorithm on the CM2

This report describes a number of implementations on the massively parallel SIMD machine called the Connection Machine of the artificial neural network algorithm developed within the SANS project. The algorithm uses a recurrent network with the connection strengths defined according to Bayesian probability estimates. The purpose of these implementations has been to study how the algorithm can be adapted to run on parallel hardware and what can be gained from using such hardware.

Björn Levin

[1] Alexander Singer,et al. Implementations of artificial neural networks on the Connection Machine , 1990, Parallel Comput..

[2] Jill P. Mesirov,et al. An Efficient Implementation of the Back-propagation Algorithm on the Connection Machine CM-2 , 1989, NIPS.

[3] Örjan Ekeberg,et al. A One-Layer Feedback Artificial Neural Network with a Bayesian Learning Rule , 1989, Int. J. Neural Syst..

[4] Shun-ichi Amari,et al. Characteristics of sparsely encoded associative memory , 1989, Neural Networks.

[5] Örjan Ekeberg,et al. Reliability and Speed of Recall in an Associative Network , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.