Neuronic convolution model for spatiotemporal information representation and processing

How to represent spatiotemporal information in an artificial neuron model has been a problem of long-standing interest in artificial intelligence. After a brief review of recent advances, Caianiello´s neuronic convolutional model (1961) is extended in this paper for spatiotemporal information representation. The kernel functions that correspond to the convolutional neuron´s receptive field profile can be described by neural wavelets. The convolutional neuron-based multilayer network and its back propagation algorithm are developed to perform spatiotemporal pattern processing. The results provide a natural framework for the discussion of spatiotemporal information representation in an artificial neural network