In the present paper we investigate four relatively independent issues, which complete our knowledge regarding the computational aspects of popular Hopfield nets. In Section 2 of the paper, the computational equivalence of convergent asymmetric and Hopfield nets is shown with respect to network size. In Section 3, the convergence time of Hopfield nets is analyzed in terms of bit representations. In Section 4, a polynomial time approximate algorithm for the minimum energy problem is shown. In Section 5, the Turing universality of analog Hopfield nets is studied.peerReviewe
The main contribution of the present work is showing that the known convergence properties of the Ho...
We approximately solve, by reduction to Maximum Clique, the graph k-coloring NP-hard problem in a bi...
Artificial neural networks have been studied for many years in the hope of achieving human-like perf...
There are three main results in this dissertation. They are PLS-completeness of discrete Hopfield ne...
It is shown that conventional computers can be exponentiallx faster than planar Hopfield networks: a...
We consider polynomial-time algorithms for finding approximate solutions of the ground state problem...
We prove that polynomial size discrete Hopfield networks with hidden units compute exactly the class...
The work deals with the Hopfield networks and uses the vector description of the theory, rather then...
This work aims at reviewing some of the main issues that are under research in the field of Hopfield...
In 1943, McCulloch and Pitts introduced a discrete recurrent neural network as a model for computati...
We review some recent rigorous results in the theory of neural networks, and in particular on the th...
We review some recent rigorous results in the theory of neural networks, and in particular on the th...
AbstractThe global convergence and asymptotic stability of Hopfield neural networks are known to be ...
We establish a fundamental result in the theory of continuous-time neural computation, by showing th...
The performance of a Hopfield network in learning an extensive number of concepts having access only...
The main contribution of the present work is showing that the known convergence properties of the Ho...
We approximately solve, by reduction to Maximum Clique, the graph k-coloring NP-hard problem in a bi...
Artificial neural networks have been studied for many years in the hope of achieving human-like perf...
There are three main results in this dissertation. They are PLS-completeness of discrete Hopfield ne...
It is shown that conventional computers can be exponentiallx faster than planar Hopfield networks: a...
We consider polynomial-time algorithms for finding approximate solutions of the ground state problem...
We prove that polynomial size discrete Hopfield networks with hidden units compute exactly the class...
The work deals with the Hopfield networks and uses the vector description of the theory, rather then...
This work aims at reviewing some of the main issues that are under research in the field of Hopfield...
In 1943, McCulloch and Pitts introduced a discrete recurrent neural network as a model for computati...
We review some recent rigorous results in the theory of neural networks, and in particular on the th...
We review some recent rigorous results in the theory of neural networks, and in particular on the th...
AbstractThe global convergence and asymptotic stability of Hopfield neural networks are known to be ...
We establish a fundamental result in the theory of continuous-time neural computation, by showing th...
The performance of a Hopfield network in learning an extensive number of concepts having access only...
The main contribution of the present work is showing that the known convergence properties of the Ho...
We approximately solve, by reduction to Maximum Clique, the graph k-coloring NP-hard problem in a bi...
Artificial neural networks have been studied for many years in the hope of achieving human-like perf...