In the neuro-computer the study processing mode

摘要

A learning system in a neuron computer comprises a neural network for receiving an analog signal from a first analog bus through an analog input port in a time divisional manner and performing a sum-of-the-products operation, and outputting an analog output signal to a second analog bus, a control pattern memory for storing a pattern of a signal for controlling the neural network, a sequencer for producing an address of said control pattern memory and a weight memory, a weight memory for storing weight data of the analog neuro processor, and digital control unit for controlling said neural network, control pattern memory, sequencer, and weight data, and for executing a learning algorithm. The learning system further includes input control unit provided on the input side of the neural network for selecting an input signal for executing an algorithm input from said digital control means or an analog input signal input from the analog input port.