TAG (training by adaptive gain) is a new adaptive neural network model for large-scale optical implementations. For single-layer neural networks withN input andM output neurons, the TAG model contains two different types of interconnections, i.e.MN global fixed interconnections and (N+M) adaptive gain controls. The training algorithm is based on gradient descent and error back-propagation, and is easily extensible to multilayer and/or higher-order architectures. For large-scale electrooptic implementation, the fixed global interconnections may be implemented by multifacet hologram, volume hologram or ground glass, and the adaptive gains by spatial light modulators (SLMs). The ground glass is more advantageous for random interconnections, with much higher diffraction efficiency and interconnection density. Both feed-forward signal and error back-propagation paths are implemented by a single ground glass, and adaptive learning has been demonstrated for heteroassociative memory and classifier.
[1]
S Y Lee,et al.
Programmable quadratic associative memory using holographic lenslet arrays.
,
1989,
Optics letters.
[2]
H. J. Caulfield,et al.
Optical neural networks
,
1989
.
[3]
S Y Lee,et al.
Parallel N(4) weighted optical interconnections: comments.
,
1988,
Applied optics.
[4]
H J Caulfield.
Parallel N(4) weighted optical interconnections.
,
1987,
Applied optics.
[5]
Soo-Young Lee,et al.
TAG: A Neural Network Model for Large-Scale Optical Implementation
,
1991,
Neural Computation.
[6]
S Y Lee,et al.
Optical implementation of the Hopfield model for two-dimensional associative memory.
,
1988,
Optics letters.