DESIGN AND CHARACTERIZATION OF AN OPTOELECTRONIC NEURAL CHIP

We present a prototype integrated circuit design suitable for use as a neural backplane in an optoelectronic artificial neural network. The device consists of a 4 x 4 array of optical input, electronic output p rocessing elements. The processing elements can sample the temporally multiplexed grey scale generated by a binary mode ferroelectric liquid crystal spatial light modulator. They implement the post-synaptic sum ming, have a programmable thresholding function, and can respond to bo th positive and negative activations - a requirement of many artificia l neural network models.