Efficient Associative Memory Based on a Nonlinear Function Constitution and Dynamic Synapses
Nonlinear function constitution and dynamic synapses, against spurious state for Hopfield neural network are proposed. The model of the dynamical connection weight and the updating scheme of the states of neurons are given. Nonlinear function constitution improves the conventional Hebbian learning rule with linear outer product method. Simulation results show that both nonlinear function constitution and dynamic synapses can effectively increase the ability of error tolerance; furthermore, associative memory of neural network with the new method can both enlarge attractive basin and increase storage capacity.
Helen Zhang, Gang Shen and David Jin
M. Xia et al., "Efficient Associative Memory Based on a Nonlinear Function Constitution and Dynamic Synapses", Advanced Materials Research, Vols. 225-226, pp. 479-482, 2011