A Neural Network for the Retrieval of Superimposed Connection Patterns

Abstract

The principle of associative memory is extended to a system with dynamical links capable of retrieval of superimposed connection patterns. The system consists of formalized neurons. Its dynamics is described by two separate Hamiltonians, one for spins and one for links. The spin part is treated in analogy to the Ising system on a 2D grid. Several such network patterns, related by permutations of neurons, are superimposed. Energy minima correspond to the activation of one connection pattern and the deactivation of all others. One important application of this system is invariant pattern recognition.