abstract |
An all-optical, continuous-time, recurrent neural network is capable of executing a broad class of energy-minimizing neural algorithms. The network is a resonator which contains a saturable, two-beam amplifier (7, Fig 3) two volume holograms, 12, 14 and a linear, two-beam amplifier 16. The saturable amplifier permits, through the use of a spatially patterned signal beam, the realization of a two-dimensional optical neuron array; the two volume holograms provide adaptive, global network interconnectivity; and the linear amplifier supplies sufficient resonator gain to permit convergent operation of the network. n<IMAGE> |