A NEURAL ARCHITECTURE FOR PATTERN SEQUENCE VERIFICATION THROUGH INFERENCING

We discuss LAPART, a neural network architecture for logical inferencing and supervised learning. We emphasize its use in recognizing familiar sequences of patterns by verifying pattern pairs inferred from prior experience. As demonstrated, LAPART can be trained to recognize multiframe sequences of patterns from imaging sensors. It consists of interconnected adaptive resonance theory (ART) networks, originated by Carpenter and Grossberg [1] for pattern classification through unsupervised learning. The interconnects enable LAPART to learn to infer one pattern class from another to form a predictive sequence. It predicts a next pattern class based upon recognition or a current pattern and tests the prediction as new data become available. A confirmed prediction aids verification of a familiar sequence, and a disconfirmation flags a novel pairing of patterns. We present a simulation of LAPART applied to verification of a hypothetical, known target using a sequence of sensor images obtained along a predetermined approach path. We address application issues with a simple strategy and indicate how they could be addressed in a more complete fashion. Other topics, including a logical interpretation of ART and LAPART, are discussed in the-appendices.