Competitive optical learning with winner-take-all modulators
Kevin H. Wagner, Timothy M. Slagle · Optical Society of America Annual Meeting · 1992
The optical implementation of modern neural network learning models such as competitive learning networks, resonance correlation networks, and back propagation networks requires a wider range of neuron behavior than a simple saturating threshold non-linearity. However, optical implementation of neurons that incorporate non-local, non-linear functions such as shunting inhibition, winner-take-all, and history-dependent behavior is beyond the capability of conventional optical devices. A new class of light modulator has been developed that combines the flexibility of analog and digital electronic VLSI circuits, optical detectors, and the switchable electo-optic capabilities of liquid crystal materials. In this paper we will show how these liquid crystal/VLSI modulators can be used in optical implementations of these learning networks.1 We will discuss in detail a competitive optical learning network that uses LC/VLSI winner-take-all neurons on fractal grids to program adaptive volume holographic interconnections.2