Modelling neural networks
โ Scribed by Bikas K. Chakrabarti; Prabir K. Dasgupta
- Publisher
- Elsevier Science
- Year
- 1992
- Tongue
- English
- Weight
- 720 KB
- Volume
- 186
- Category
- Article
- ISSN
- 0378-4371
No coin nor oath required. For personal study only.
โฆ Synopsis
We review here briefly some of our recent studies on neural network modelling. We discuss the studies on relaxation and growth of correlation in the Hopfield model, increase in memory loading capacity with an extended Hopfield-like model with delayed dynamics, the prediction capability of time series with a multi-layered network with supervised learning and studies on some generalised versions of the travelling salesman problem.
๐ SIMILAR VOLUMES
Up to now, a number of models have been proposed and discussed to describe a wide range of inelastic behaviours of materials. The fatal problem of using such models is however the existence of model errors, and the problem remains inevitably as far as a material model is written explicitly. In this