论文信息 - Sparse distributed memory implementations on tree shape parallel neurocomputer

Sparse distributed memory implementations on tree shape parallel neurocomputer

This paper presents two different realizations of a sparse distributed memory (SDM) model. For parallelization purposes, addressing, storage and retrieval operations are explained in detail and some existing implementations in various computing platforms are considered before introducing the tree shaped parallel computer, TUTNC (Tampere University of Technology Neural Computer). The architecture and main features of TUTNC are presented in order to map SDM to the system in columnwise and rowwise manner. Mappings are compared in terms of measured execution time with different parameter sets. Speedup and performance estimations are also given for a larger system. The results show, that SDM can be well parallelized in TUTNC.

T. Hamalainen

[1] Douglas G. Danforth,et al. An empirical investigation of sparse distributed memory using discrete speech recognition , 1990 .

[2] Bertil Svensson,et al. Using and Designing Massively Parallel Computers for Artificial Neural Neural Networks , 1992, J. Parallel Distributed Comput..

[3] Timo Hämäläinen,et al. TUTNC: a general purpose parallel computer for neural network computations , 1995, Microprocess. Microsystems.

[4] Richard W. Prager,et al. The modified Kanerva model for automatic speech recognition , 1989 .

[5] K. Kaski,et al. Neural networks and MIMD-multiprocessors , 1990 .

[6] Michael J. Flynn,et al. Sparse distributed memory prototype: principles and operation , 1989 .

[7] David Rogers,et al. Kanerva's Sparse Distributed Memory: an Associative Memory Algorithm Well-Suited to the Connection Machine , 1989, Int. J. High Speed Comput..

[8] Pentti Kanerva,et al. Sparse distributed memory and related models , 1993 .

[9] Simon Haykin,et al. Neural Networks: A Comprehensive Foundation , 1998 .

[10] Jukka Saarinen,et al. VLSI architectures of sparse distributed memory , 1991, 1991., IEEE International Sympoisum on Circuits and Systems.

[11] Kimmo Kaski,et al. Highly Parallel Realization of Sparse Distributed Memory System , 1991, The Sixth Distributed Memory Computing Conference, 1991. Proceedings.