Local interconnection neural network and its optical implementation

Abstract Based on the Hopfield model, a new concept of local interconnection neural network (LINN) is proposed. Compared with the global interconnection neural network (GINN), LINN has a relatively smaller interconnection matrix as well as the same ability of associative memory. Three optical implementation schemes are proposed, and experimental results are also presented.

[1]  X M Wang,et al.  Neural network model for unequally distributed neuron states. , 1992, Applied optics.

[2]  K Noguchi.  Large-scale two-dimensional optical Hopfield associative memory using an incoherent optical free-space interconnection. , 1991, Optics letters.

[3]  F T Yu,et al.  Two-dimensional programmable optical neural network. , 1989, Applied optics.

[4]  H H Arsenault,et al.  Optical associative memory model based on neural networks having variable interconnection weights. , 1987, Applied optics.

[5]  T H Yoon,et al.  Associative-memory model based on neural networks: modification of Hopfield model. , 1988, Optics letters.

[6]  H Stark,et al.  Projection method formulations of Hopfield-type associative memory neural networks. , 1990, Applied optics.

[7]  Demetri Psaltis,et al.  Optical Associative Memory Using Fourier Transform Holograms , 1987 .

[8]  D Psaltis,et al.  Optical implementation of the Hopfield model. , 1985, Applied optics.

[9]  X Yang,et al.  Space-time-sharing optical neural network. , 1991, Optics letters.

[10]  S Y Lee,et al.  Optical implementation of the Hopfield model for two-dimensional associative memory. , 1988, Optics letters.

[11]  X Yang,et al.  Optical neural network with pocket-sized liquid-crystal televisions. , 1990, Optics letters.

[12]  Jiajun Zhang,et al.  Two‐dimensional inner‐product model for auto‐hetero‐associative memory and its new optoelectronic implementation , 1992 .

[13]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Y Ichioka,et al.  Hopfield model with multistate neurons and its optoelectronic implementation. , 1991, Applied optics.

[15]  J Ohta,et al.  Optical implementation of large-scale neural networks using a time-division-multiplexing technique. , 1990, Optics letters.