초록 ▼

A analog data neural network processing system is provided in which there is a self optimization capability that varies the signal processing factors in response to a detected contrast in the system output patterns. The system provides feedback type guidance in varying such processing factors as sam

A analog data neural network processing system is provided in which there is a self optimization capability that varies the signal processing factors in response to a detected contrast in the system output patterns. The system provides feedback type guidance in varying such processing factors as sampling rate, frame length, signal transformation, neural network vigilance and architecture, each in a direction that will maximize or minimize the contracts with patterns used to train the network. The processing system is useful in all signal classification tasks.

대표청구항 ▼

[ What is claimed is:] [1.]1. A neural network signal classifier system, wherein an analog data signal input is processed in multiple stages before being provided to a neural network, the system comprising in combination:a separate adjustable element for each signal processing stage of said multiple

[ What is claimed is:] [1.]1. A neural network signal classifier system, wherein an analog data signal input is processed in multiple stages before being provided to a neural network, the system comprising in combination:a separate adjustable element for each signal processing stage of said multiple stages for influencing overall performance of the classifier system;means for recognizing an output pattern contrast with a preset desired confidence; and,an optimization guidance capability having means for delivering a guidance adjustment signal to each said signal processing stage, said adjustment signal being responsive to said output pattern contrast.