With a neural network classifier for adaptive filters

摘要

An adaptive filtering neural network classifier for classifying input signals, includes a neural network (50) and one or more adaptive filters (15a-n) for receiving input analog signals to be classified and generates inputs for the classifier. Each adaptive filter is characterized as having a predetermined number of operating parameters. An A/D converter (30) converts each input signal to a digital signal before input to neural network. The neural network processes each signal to generate a plurality of weighted output signals. One of the output signals represents a class for the input signal, and an error signal representing difference between output signal and predetermined desired output is generated. A control device (65) responsive to the error signal generates operating filter parameters for input to adaptive filter to minimize error signal.