Showing papers on "Artificial neural network published in 1979"
62 citations
TL;DR: It is shown that given the network connectivity it is possible to predict autonomous dynamic behaviour, as well as behaviour following hyperpolarizing or depolarizing inputs to neurons of the network, given information about patterns of firing activity during cycles and transients of neural networks.
34 citations
TL;DR: The maximum periods of transitions of 2-dimensional uniform neural networks with Neumann neighbors are investigated and the maximum period is finite in case that the refractory period is 1 or 3.
Abstract: The maximum periods of transitions of 2-dimensional uniform neural networks with Neumann neighbors are investigated. As for excitatory neural networks, the maximum period is finite in case that the refractory period is 1 or 3, but the refractory periods realizing unbounded period of transitions range from 2 to infinity which are different from the case of 1-dimensional networks. Results are obtained by constructing periodic configurations directly.
19 citations
TL;DR: A computer-simulated mechanism is developed here, based on the probabilistic neural model previously developed by Anninos, Csermeley & Harth, which is identified with the cross-reference mechanism which is assumed to be the basis of memory growth.
4 citations
TL;DR: Mutual inhibition between neurons combined with a learning principle similar to that proposed by Hebb is shown to secure a powerful selforganizing property for neural networks.
Abstract: Mutual inhibition between neurons combined with a learning principle similar to that proposed by Hebb is shown to secure a powerful selforganizing property for neural networks. Numerical analysis reveals that the system investigated always organizes itself into the same final state from any arbitrarily chosen initial state.
1 citations