Image restoration using a modified Hopfield network
- 1 January 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 1 (1) , 49-63
- https://doi.org/10.1109/83.128030
Abstract
A modified Hopfield neural network model for regularized image restoration is presented. The proposed network allows negative autoconnections for each neuron. A set of algorithms using the proposed neural network model is presented, with various updating modes: sequential updates; n-simultaneous updates; and partially asynchronous updates. The sequential algorithm is shown to converge to a local minimum of the energy function after a finite number of iterations. Since an algorithm which updates all n neurons simultaneously is not guaranteed to converge, a modified algorithm is presented, which is called a greedy algorithm. Although the greedy algorithm is not guaranteed to converge to a local minimum, the l (1) norm of the residual at a fixed point is bounded. A partially asynchronous algorithm is presented, which allows a neuron to have a bounded time delay to communicate with other neurons. Such an algorithm can eliminate the synchronization overhead of synchronous algorithms.Keywords
This publication has 16 references indexed in Scilit:
- Iterative Image Restoration AlgorithmsPublished by Taylor & Francis ,2009
- Image restoration using the Hopfield network with nonzero autoconnectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A regularized iterative image restoration algorithmIEEE Transactions on Signal Processing, 1991
- On the convergence properties of the Hopfield modelProceedings of the IEEE, 1990
- A generalized convergence theorem for neural networksIEEE Transactions on Information Theory, 1988
- Image restoration using a neural networkIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Neural networks for computation: number representations and programming complexityApplied Optics, 1986
- Decreasing energy functions as a tool for studying threshold networksDiscrete Applied Mathematics, 1985
- Optical implementation of the Hopfield modelApplied Optics, 1985
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982