Modified high-order neural network for invariant pattern recognition

摘要

A modification for high-order neural networks (HONN) is described. The proposed modified HONN takes into account prior knowledge of the binary patterns that must be learned. This significantly reduces hence computation time as well as memory requirements for network configuration and weight storage. An "approximately equal triangles" scheme for weight sharing is also proposed. These modifications enable the efficient computation of HON Ns for image fields of greater that 100 x 100 pixels without any loss of pattern information.