A PROTOTYPE 3D OPTICALLY INTERCONNECTED NEURAL-NETWORK

We report the implementation of a prototype three-dimensional (3D) optoelectronic neural network that combines fi ee-space optical interconnects with silicon-VLSI-based optoelectronic circuits. The prototype system consists of a 16-node input, 4-neuron hidden, and a single-neuron output layer, where the denser input-to-hidden-layer connections are optical. The input layer uses PLZT light modulators to generate optical outputs which are distributed over an optoelectronic neural network chip through space-invariant holographic optical interconnects. Optical interconnections provide negligible San-out delay and allow compact, purely on-chip electronic H-tree type San-in structure. The small prototype system achieves a measured 8-bit electronic San-in precision and a calculated maximum speed of 640 million interconnections pet second. The system was tested using synaptic weights learned off-system and was shown to distinguish any vertical line from any horizontal one in an image of 4 x 4 pixels. New, more efficient light detector and small-area analog synaptic circuits and denser optoelectronic neuron layouts are proposed to scale lip the system. A high-speed, Seed-forward optoelectronic synapse implementation density of lip to 10(4)/cm(2) seems feasible using new synapse design. A scaling analysis of the system shows that the optically interconnected neural network implementation can provide higher San-in speed and lower power consumption characteristics than a purely electronic, crossbar-based neural network implementation.