The Lockheed probabilistic neural network processor

The probabilistic neural network processor (PNNP) is a custom neural network parallel processor optimized for the high-speed execution (three billion connections per second) of the probabilistic neural network (PNN) paradigm. The PNNP's massively parallel circuitry can solve pattern recognition and classification problems many orders of magnitude faster than a software simulation of the PNN paradigm. When combined with the instant learning capability of the PNN paradigm, full investigations of large database problems can be done in a very short time. Real-time devices may be attached to the PNNP to show adaptability of the classifier in a dynamic environment.<<ETX>>