Sequential simulation of parallel iterations and applications
TLDR
It is shown that the parallel evolution of a network of automata N can be sequentially simulated by another network N′ whose local transition functions are the same as those of N.About:
This article is published in Theoretical Computer Science.The article was published on 1986-12-30 and is currently open access. It has received 20 citations till now. The article focuses on the topics: Automata theory & Quantum finite automata.read more
Citations
More filters
Journal ArticleDOI
General-purpose computation with neural networks: a survey of complexity theoretic results
Jiří Šíma,Pekka Orponen +1 more
TL;DR: This work surveys and summarizes the literature on the computational aspects of neural network models by presenting a detailed taxonomy of the various models according to their complexity theoretic characteristics, mainly on the digital computation whose inputs and outputs are binary in nature, although their values are quite often encoded as analog neuron states.
Journal ArticleDOI
Computing with truly asynchronous threshold logic networks
TL;DR: Simulation mechanisms by which any network of threshold logic units with either symmetric or asymmetric interunit connections can be simulated on a network, but without any a priori constraints on the order of updates of the units are presented.
Journal Article
Exponential Transient Classes of Symmetric Neural N etworks for Synchronous and Sequential Updating
Eric Goles,A Servet Martínez +1 more
TL;DR: A class of symmetric neural networks which synchronous iteration possesses an exponen tial transient length is exhibited, and if {I, ..., n} is the set of nodes it is proved the transient length satisfies T 2: 2 n / 3.
Complexity Issues in Discrete Hopfield Networks
Patrik Floréen,Pekka Orponen +1 more
TL;DR: Parberry et al. as mentioned in this paper survey some aspects of the computational complexity of discrete-time and discrete-state Hopfield networks, focusing on the complexity of the synthesis (learning) and analysis problems related to Hopfield nets as associative memories.
Journal ArticleDOI
The computational power of discrete hopfield nets with hidden units
TL;DR: It is proved that polynomial size discrete Hopfield networks with hidden units compute exactly the class of Boolean functions PSPACE/poly, i.e., the same functions as are computed by polynometric space-bounded nonuniform Turing machines.
References
More filters
Journal ArticleDOI
Decreasing energy functions as a tool for studying threshold networks
TL;DR: Block sequential iterations of threshold networks are studied through the use of a monotonic operator, analogous to the spin glass energy, which allows to characterize the dynamics: transient and fixed points.
Journal ArticleDOI
On periodical behaviour in societies with symmetric influences
Svatopluk Poljak,Miroslav Sůra +1 more
TL;DR: It is proved that the length of the period of a simple model of society with a symmetric functionw(u, v) measuring the influence of the opinion of memberv on that of memberu is either one or two.
Journal ArticleDOI
Transient length in sequential iteration of threshold functions
TL;DR: A general bound on the transient length for a sequential iteration on F, a function from {0,1}n into itself whose components are symmetric threshold functions, is given.
Journal ArticleDOI
Decision equation for binary systems. Application to neuronal behavior.
E. E. Caianiello,A. De Luca +1 more
TL;DR: The exact mathematical treatment is given for a non linear equation describing the delayed yes-or-no response to a binary system to external stimulations, in some typical cases of interest.
Journal ArticleDOI
Iterative behaviour of generalized majority functions
Eric Goles,M. Tchuente +1 more
TL;DR: In this article, Tchuente et al. studied the dynamical behavior of such a society under local majority rules and provided algebraic invariants analogous to those exhibited in Goles (1980) for the study of Boolean threshold functions.
Related Papers (5)
A logical calculus of the ideas immanent in nervous activity
Warren S. McCulloch,Walter Pitts +1 more
Exponential Transient Classes of Symmetric Neural N etworks for Synchronous and Sequential Updating
Eric Goles,A Servet Martínez +1 more