Networks of Formal Neurons and Memory Palimpsests
Jean‐Pierre Nadal, G. Toulouse, J P Changeux, Stanislas Dehaene · Europhysics Letters (EPL) · 1986
One characteristic behaviour of the Hopfield model of neural networks, namely the catastrophic deterioration of the memory due to overloading, is interpreted in simple physical terms. A general formulation allows for an exploration of some basic issues in learning theory. Two learning schemes are constructed, which avoid the overloading deterioration and keep learning and forgetting, with a stationary capacity.