Optical associative memory with invariances
- 4 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 291-301
- https://doi.org/10.1109/cnna.1990.207534
Abstract
A single-slab second order neural network model with scale and translation invariances is proposed. This is based on the backpropagation learning rule by using group theory to impose the invariances to the network. The results show that full range translation invariance and a limited range of scale invariance are realisable. The performance of outer-product model with invariance is analysed. Then an inner-product associative memory model with translation invariance is proposed. A strictly increasing nonlinear operation which is cooperated with a sign function is chosen to guarantee the correct recall convergence of the network without iteration. The performance of network is improved drastically. These two models can be implemented by simple optical systems with parallel processing capability Author(s) Yang, G.G. Dept. of Eng. Sci., Oxford Univ., UKKeywords
This publication has 5 references indexed in Scilit:
- Optoelectronic chip implementation of a quadratic associative memoryOptics Letters, 1990
- Learning by diffusion for multilayer perceptronElectronics Letters, 1989
- A Polarization Based Optical Connectionist MachinePublished by SPIE-Intl Soc Optical Eng ,1989
- Shift-Invariant Optical Associative MemoriesOptical Engineering, 1987
- Optical implementation of the Hopfield modelApplied Optics, 1985