An Internal Mechanism for Detecting Parasite Attractors in a Hopfield Network
- 1 September 1994
- journal article
- Published by MIT Press in Neural Computation
- Vol. 6 (5) , 902-915
Abstract
This paper presents a built-in mechanism for automatic detection of prototypes (as opposed to parasite attractors) in a Hopfield network. It has a good statistical performance and avoids host computer overhead for this purpose. This mechanism is based on an internal coding of the prototypes during learning, using cyclic redundancy codes, and leads to an efficient implementation in VLSI. The immediate separation of prototypes from parasite attractors can be used to enhance the autonomy of the networks, aiming at hierarchical multinetwork structures. As an example, the use of such an architecture for the classification of handwritten digits is described.Keywords
This publication has 10 references indexed in Scilit:
- Specification and implementation of a digital Hopfield-type associative memory with on-chip trainingIEEE Transactions on Neural Networks, 1992
- A digital CMOS fully connected neural network with in-circuit learning capability and automatic identification of spurious attractors1991
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- An introduction to neural computingNeural Networks, 1988
- Parallel architectures for artificial neural nets1988
- Learning of correlated patterns in spin-glass networks by local learning rulesPhysical Review Letters, 1987
- Collective computational properties of neural networks: New learning mechanismsPhysical Review A, 1986
- Stochastic Dynamics of Neural NetworksIEEE Transactions on Systems, Man, and Cybernetics, 1986
- Spin-glass models of neural networksPhysical Review A, 1985
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982