Abstract
Most current neural nets experiments use the MultiLayer Perceptrons and the Backpropagation learning algorithms. Whereas the experimentation speed is insufficient, few analog integrated circuits have been realized for these algorithms, because neither their implementation nor their parallelization are obvious. On the other hand, Boltzmann Machines (Hinton et Sejnowski 1984) show a number of very attractive features, including high recognition rates, but their simulations are desperately slow. Therefore mixed analog/digital implementations have been described (Alspector et al 1987a, Alspector et al 1987b, Kreuzer et al 1988), whose learning algorithm is hardwired.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alspector J. & al., “Stochastic learning network and their electronic implementation”, Procs N.I.P.S., A.I.P., 1987
Alspector J. et al., “A neuromorphic V.L.S.I. learning system”, Stanford Conference on VLSI, M.I.T. Press, 1987
Alspector J. et al., “Relaxation Networks for Large Supervised Learning Problems”, Procs N.I.P.S., 90
Alspector J. et al., “A VLSI-efficient Technique for Generating Multiple Uncorrelated Noise Sources and its Application to Stochastic Neural Network”, JSSC, vol. SC-38, pp. 109–123, 1991
Arima et al, “A 336-Neuron, 28K-Synapse, Self-Learning Neural Network Chip with Branch- Neuron-Unit Arcchitecture” JSSC, vol. SC-26, pp. 1637–1644, 91
Azencott R., “Synchronous Boltzmann Machines and their learning algorithms”, Neurocomputing, Les Arcs, 1989, Springer-Verlag NATO ASI Series, Vol. F-68
Azencott R., “Boltzmann Machines: high-order interactions and Synchronous learning”, Procs Stochastic models, statistical methods and algorithms in image analysis, Ed. by P. Barone and A. Frigessi, Lecture Notes in Statistics, Springer-Verlag, 1990
Belhaire E. et al., “A linear “sum-of-product” circuit for Boltzmann machines”, ISCAS 91, Singapore, June 11–14 1991, pp. 1299 – 1302
Belhaire E. et al., “A faithful analog implementation of the Boltzmann Machine”, ICANN 92, Brighton, September 4–7 1992
Garda P. et al., “An analog circuit with digital I/O for Synchronous Boltzmann Machines”, VLSI for Artificial Intelligence and Neural Networks, Oxford, September 2–4 1990, Ed. by J. Delgado-Frias et W. Moore, Plenum Publishing Corp., 1991, pp. 245–253
Hinton G. et al., “Boltzmann Machines”, C.M.U. Technical Report CMU-CS-84–119, Carnegie Mellon University, 1984
Hortensius P. et al, “Cellular Automata-Based Pseudorandom Number Generators for Built-in Self Test”, IEEE Trans, on CAD, Vol. 8, pp. 842–859, 89
Kreuzer I. et al., “A modified model of Boltzmann Machines for W.S.I, realization”, Signal Processing IV, 1988
Lacaille J., “Machines de Boltzmann, Théorie et Applications”, Ph.D. Thesis, June 25th 1992, University of Paris Sud
Wolfram S., “Random Sequence Generation by Cellular Automata”, Advances in Applied Mathematics, 7, pp. 123–169, 1986
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer Science+Business Media New York
About this chapter
Cite this chapter
Lafargue, V., Garda, P., Belhaire, E. (1994). An Analog Implementation of the Boltzmann Machine with Programmable Learning Algorithms. In: Delgado-Frias, J.G., Moore, W.R. (eds) VLSI for Neural Networks and Artificial Intelligence. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-1331-9_4
Download citation
DOI: https://doi.org/10.1007/978-1-4899-1331-9_4
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-1333-3
Online ISBN: 978-1-4899-1331-9
eBook Packages: Springer Book Archive