A neuro-chip for real-time learning, processing and control

We present results of several experiments of a neural network with temporal learning on a single chip. The single chip configuration is a 2-D scalable array with learning constructed via simple modular CMOS building blocks. We report on learning prototype periodic temporal signals which may be displayed as a closed curve, a figure-8 shape, or an arbitrary periodic or aperiodic shapes in the state space. The experiments demonstrate the instantaneous learning by the chip of these shapes