Logical Connectionist Systems
A universal node model is assumed in this general analysis of connectionist nets. It is based on a logic truth-table with a probabilistic element. It is argued that this covers other definitions. Algorithms are developed for training and testing techniques that involve reducing amounts of noise, giving a new perspective on annealing. The principle is further applied to ‘hard’ learning and shown to be achievable on the notorious parity-checking problem. The performance of the logic-probabilistic system is shown to be two orders of magnitude better than know back-error propagation techniques which have used this task as a benchmark.
KeywordsParity Checker Trained State Connectionist System Boltzmann Machine Probabilistic Node
Unable to display preview. Download preview PDF.
- 1.Rumelhart D.E. and McClelland J.L.., (eds.) : Parellel Distributed Processing, Vol. 1 & Vol 2, MIT Press, Cambridge, Mass, 1986.Google Scholar
- 3.Hopfield J.J., : Neural Networks and Physical Systems with Emergent Computational Abilities, Proceedings of the National Academy of Sciences, U.S.A., Vol. 79, pp. 2554–2558, 1982.Google Scholar
- 6.Rumelhart D.E., Hinton G.E., and Williams R.J., : Learning Internal Representations by Error Propagation, in Rumelhart D.E. and McClelland J.L., (eds.) : Parallel Distributed Processing, Vol. 1, MIT Press, Cambridge, Mass, 1986.Google Scholar
- 8.Hinton G.E., Sejnowski T.J., Ackley, D.H., : Boltzmann Machines: Constraint Satisfaction Networks that Learn, Tech. Rep. CMU CS 84 119, Carnegie Mellon University, Pittsburgh, 1984.Google Scholar
- 11.Aleksander I., : The Logic of Connectionist Systems, Neural Net Research Report, Imperial College, London, August 1987.Google Scholar