The theory of neural networks is extended to include discrete neurons with more than two
discrete states. The dynamics of such systems are studied. The maximum number of storage …

We consider certain simple neural network models of associative memory with N binary
neurons and symmetric lth order synaptic connections, in which m randomly chosen N-bit …

The stochastic dynamics of randomly asymmetric fully connected Ising systems is studied.
We solve analytically the particularly simple case of fully asymmetric systems. We calculate …

The Hopfield model of neural networks is extended to allow for the storage and retrieval of
hierarchically correlated patterns. The overlaps between these patterns form an ultrametric …

We have measured the ac nonlinear susceptibilities χ 3', χ 5', and χ 7'of very dilute AgMn
spin glasses above and below the transition temperature T g as a function of frequency …

The Sparse, Distributed Memory (SDM) model (Kanerva, 1984) is compared to Hopfield-
type, neural-network models. A mathematical framework for comparing the two models is …

We discuss nonexponential relaxation in spin glasses and glasses above the ordering
temperature T g in terms of the morphology of the set of available states in configuration …

This paper presents rigorous mathematical proofs for some observed convergence
phenomena in an associative memory model introduced by Hopfield (based on Hebbian …

The authors study the attractors in an infinite-range Ising spin-glass model with deterministic
dynamics where the interactions have asymmetry, specified by a parameter k. They find a …

Direct observations of the magnetization structure in two reentrant spin-glass alloys
[polycrystalline Ni 1− x Mn x and amorphous (Fe 78 Mn 22) 75 P 16 B 6 Al 3] near liquid …