An Exactly Solvable Asymmetric Neural Network Model
Europhysics Letters (EPL)Published 15 July 1987Open access
Bernard Derrida, E. Gardner, Alfred Zippelius
Citations552
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A diluted and nonsymmetric version of the Little-Hopfield model is considered which can be solved exactly and it is shown that even when the system remembers, two different configurations which remain close to the same pattern never become identical.
Abstract
We consider a diluted and nonsymmetric version of the Little-Hopfield model which can be solved exactly. We obtain the analytic expression of the evolution of one configuration having a finite overlap on one stored pattern. We show that even when the system remembers, two different configurations which remain close to the same pattern never become identical. Lastly, we show that when two stored patterns are correlated, there exists a regime for which the system remembers these patterns without being able to distinguish them.
Keywords
Computer ScienceNeuroscience
Proceedings of the National Academy of SciencesNeural networks and physical systems with emergent collective computational abilities.
19,349 Citations1982J. J. Hopfield
A model of a system having a large number of simple equivalent components, based on aspects of neurobiology but readily adapted to integrated circuits, produces a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.
Proceedings of the National Academy of SciencesNeurons with graded response have collective computational properties like those of two-state neurons.
6,955 Citations1984J. J. Hopfield
A model for a large network of "neurons" with a graded response (or sigmoid input-output relation) is studied and collective properties in very close correspondence with the earlier stochastic model based on McCulloch - Pitts neurons are studied.
Journal of Theoretical BiologyMetabolic stability and epigenesis in randomly constructed genetic nets
4,751 Citations1969Stuart Kauffman
The hypothesis that contemporary organisms are also randomly constructed molecular automata is examined by modeling the gene as a binary (on-off) device and studying the behavior of large, randomly constructed nets of these binary “genes”.
Physical review. A, General physicsSpin-glass models of neural networks
1,193 Citations1985Daniel J. Amit, Hanoch Gutfreund +1 more
Two dynamical models, proposed by Hopfield and Little to account for the collective behavior of neural networks, are analyzed and it is shown that the long-time behavior of the two models is identical, for all temperatures below a transition temperature ${T}_{c}$.
Physical Review LettersStoring Infinite Numbers of Patterns in a Spin-Glass Model of Neural Networks
1,047 Citations1985Daniel J. Amit, Hanoch Gutfreund +1 more
The Hopfield model for a neural network is studied in the limit when the number of stored patterns increases with the size of the network, as $p=\ensuremath{\alpha}N$, and it is shown that, despite its spin-glass features, the model exhibits associative memory.
Annals of PhysicsStatistical mechanics of neural networks near saturation
849 Citations1987Daniel J. Amit, Hanoch Gutfreund +1 more
The Hopfield model of a neural network near its saturation is studied, and it is found that a field coupled to many patterns has a very limited utility in enhancing their learning.
Europhysics Letters (EPL)Random Networks of Automata: A Simple Annealed Approximation
725 Citations1986Bernard Derrida, Yves Pomeau
This work gives a simple annealed approximation which predicts K = 2 as the critical value of K and gives also quantitative predictions for distances between iterated configurations.
Mathematical BiosciencesThe existence of persistent states in the brain
650 Citations1974W. A. Little
Physical Review LettersTemporal Association in Asymmetric Neural Networks
575 Citations1986Haim Sompolinsky, Ido Kanter
A neural network model which is capable of recalling time sequences and cycles of patterns is introduced and may be also useful in understanding the generation of rhythmic patterns in biological motor systems.
Journal of Physics C Solid State PhysicsPhase diagrams for dilute spin glasses
335 Citations1985L Viana, A. J. Bray
Journal of Physics A Mathematical and GeneralApplication of statistical mechanics to NP-complete problems in combinatorial optimisation
326 Citations1986Yuchen Fu, Philip W. Anderson
The authors find a spin glass transition in the system, and the low temperature phase space has an ultrametric structure, which sheds light on the nature of hard computation problems.
Physica D Nonlinear PhenomenaEmergent properties in random complex automata
255 Citations1984Stuart Kauffman
Emergent, highly ordered dynamical behavior in random automata rich in a specific class of “canalizing” Boolean functions due to the crystallization of powerful subautomata called forcing structures is discussed.
Journal de physiqueEvolution of overlaps between configurations in random Boolean networks
173 Citations1986Bernard Derrida, G. Weisbuch
Physical Review LettersMean-field theory of spin-glasses with finite coordination number
171 Citations1987Ido Kanter, Haim Sompolinsky
The mean-field theory of dilute spin-glasses is studied in the limit where the average coordination number is finite and the zero-temperature phase diagram is calculated and the relationship between the spin-glass phase and the percolation transition is discussed.
Journal of Physics A Mathematical and GeneralStructure of metastable states in the Hopfield model
119 Citations1986E. Gardner
An upper bound for the number of metastable states in the Hopfield model is calculated as a function of the Hamming fraction from an input pattern, which implies that there is a gap between a set of states close to the input pattern and another set centred around the hamming fraction 0.5 from it.
Journal de physiqueOn the approach of the stationary state in Kauffman's random Boolean network
56 Citations1987H. J. Hilhorst, M. J. P. Nijmeijer
It is shown that in this limit the average overlap between two arbitrary initial states rigorously obeys an equation first derived by Derrida and Pomeau, and that for k ≤ 2 each state evolves, in a weak sense, to a fixed point state.
Journal of Physics C Solid State PhysicsThe freezing transition in disordered non-equilibrium systems
16 Citations1986Richard Bausch, H. K. Janssen +2 more