Hopfield network


Also found in: Wikipedia.

Hopfield network

(artificial intelligence)
(Or "Hopfield model") A kind of neural network investigated by John Hopfield in the early 1980s. The Hopfield network has no special input or output neurons (see McCulloch-Pitts), but all are both input and output, and all are connected to all others in both directions (with equal weights in the two directions). Input is applied simultaneously to all neurons which then output to each other and the process continues until a stable state is reached, which represents the network output.
References in periodicals archive ?
To satisfy varied groups of customers' requirement, and according to the composition of overlap peptides, some other methods are also adopted by Creative Biolabs, including Hydrogen-deuterium exchange and mass spectrometry, Hopfield network, as well as peptide-based approaches.
In practice we have many ANN architectures, most often determined by the hidden layer's connection mode: Perceptron, Radial Basis Function Network, Multilayer Perceptron, Recurrent Neural Network, Hopfield Network, Boltzmann Machine Network, Convolutional Neural Network, Modular Neural Network, etc.
E(x, h) is the energy function, analogous to the one used on a Hopfield network [40], defined as
More than 40 types of neural network model are used frequently, which can be classified as the Hopfield network, BP neural network, RBF network, and so on [12].
He, "A generalized Hopfield network for nonsmooth constrained convex optimization: Lie derivative approach," IEEE Transactions on Neural Networks and Learning Systems, vol.
We demonstrate that an auxiliary network can indeed mitigate the effects of memory loss due to progressive neurodegeneration of the Hopfield network.
* Hopfield network: Hopfield is a kind of feedback neural network model, which has the behavior of spontaneous generation of the neural network under the high connection.
The transient dynamics of the Hopfield network is governed by the following group of differential equations:
A Hopfield network can act as an autoassociative memory network.
The continuous Hopfield network [6], firstly used in channel assignment, requires very large iteration numbers to converge and is unsuitable for decentralized wireless sensor networks.
One of the neural network models exploiting statistical dynamics is the Hopfield network [23, 24].
Having shown that feed-forward networks could only perform tasks they were repetitively trained to do, we then introduced the principles of the Hopfield network, a simple model of memory that allows unsupervised learning.