Abstract
This paper puts forward the need for neural evolution schemes that reduce the volumes of synchronization and communication required by current neural models in order to obtain efficient implementations in the parallel machines and networks of computers which are available today. In this respect, a parallel implementation of a modified Boltzmann machine is considered as an example. The neurons of the machine are distributed among the processors of the multicomputer, which asynchronously computes the evolution of their subset of neurons. In this evolution, the processors use values which may or may not be updated for the neuron states, and furthermore they do not have to wait for these values to come from other processors, thus reducing the communication requirements. Nevertheless, this lack of coherence between the neuron states in different processors is corrected by the way the processors update them with the information coming from other processors.
Preview
Unable to display preview. Download preview PDF.
References
Aarts, E.H.L.; Korst, J.H.M.:“Simulated Annealing and Boltzmann Machines”. New York: Wiley, 1988.
Oh, D.H.; Nang, J.H.; Yoon, H.; Maeng, S.R.:“An efficient mapping of Boltzmann Machine computations onto distributed-memory multiprocessors”. Microprocessing and Microprogramming, 33, pp.223–236, 1991/92.
Nang, J; Oh, D.H.; Yoon, H.; Maeng, S.R.:“A Parallel Boltzmann Machine on Distributed-Memory Multiprocessors”. Proc. of the International Joint Conference on Neural Networks (IJCNN'91), Vol.1, pp.608–613, 1991.
Benitez, J.M.; Ortega, J.; Requena, I.:“Asynchronously Parallel Boltzmann Machines Mapped onto Distributed-Memory Multiprocessors”, en “From Natural to Artificial Neural Computation”, J. Mira, F. Sandoval (Eds.) Lecture Notes in Computer Science, 930, pp.744–751. Springer, 1995.
Billard, E.A.; Pasquale, J.C.: “Adaptive Coordination in Distributed Systems with Delayed Communication”. IEEE Trans. on Syst., Man, and Cyb., Vol.25, No.4, pp.546–554. April, 1995.
Livesey, M.:“Clamping in Boltzmann Machines”. IEEE Trans. on Neural Networks, Vol2, No.1, pp.143–148. January, 1991.
Pramanick, I.; Kuhl, J.G.:“An inherently Parallel Method for Heuristic Problem-Solving: Part I — General Framework”. IEEE Trans. on Parallel and Dist. Systm., Vol6, No.10, pp.1006–1015. October, 1995.
Pramanick, I.; Kuhl, J.G.:“An inherently Parallel Method for Heuristic Problem-Solving: Part II — Example Applications”. IEEE Trans. on Parallel and Dist. Systm., Vol6, No.10, pp.1016–1028. October, 1995.
Lee, S.-Y.; Lee, K.G.:“Synchronous and Asynchronous Parallel Simulated Annealing with Multiple Markov Chains”. IEEE Trans. on Parallel and Distributed Systems, Vol.7, No.10, pp.993–1007. October, 1996.
Zissimopoulos, V.; et al.:“On the aproximation of NP-complete problems by using the Boltzmann Machine Method: The cases of some covering and packing problems”. IEEE Trans. on Comp., Vol.40, No.12, pp.1413–18. Diciembre, 1991.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ortega, J., Parrilla, L., Prieto, A., Lloris, A., Puntonet, C.G. (1997). Modified Boltzmann machine for an efficient distributed implementation. In: Mira, J., Moreno-Díaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032582
Download citation
DOI: https://doi.org/10.1007/BFb0032582
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive