| AN INFORMATION THEORETICAL APPROACH TO NEURAL NETWORKS |
| |
| 引用本文： | Caro Lucas. AN INFORMATION THEORETICAL APPROACH TO NEURAL NETWORKS[J]. 系统科学与复杂性, 1993, 0(4) |
| |
| 作者姓名： | Caro Lucas |
| |
| 作者单位： | Electrical Engineering |
| |
| 基金项目： | This work was supported in part by Tehran University grant number 708. |
| |
| 摘 要： | The purpose of this paper is to present a unified theory of several differentneural networks that have been proposed for solving various computation, pattern recog-nition, imaging, optimization, and other problems. The functioning of these networks ischaracterized by Lyapunov energy functions. The relationship between the deterministicand stochastic neural networks is examined. The simulated annealing methods for findingthe global optimum of an objective function as well as their generalization by injectingnoise into deterministic neural networks are discussed. A statistical interpretation of thedynamic evolution of the different neural networks is presented. The problem of trainingdifferent neural networks is investigated in this general framework. It is shown how thisapproach can be used not only for analyzing various neural networks, but also for the choiceof the proper neural network for solving any given problem and the design of a trainingalgorithm for the particular neural network.
|
AN INFORMATION THEORETICAL APPROACH TO NEURAL NETWORKS |
| |
| Caro Lucas Electrical Engineering Department,Tehran University,P.O. Box /,Tehran IRAN. AN INFORMATION THEORETICAL APPROACH TO NEURAL NETWORKS[J]. Journal of Systems Science and Complexity, 1993, 0(4) |
| |
| Authors: | Caro Lucas Electrical Engineering Department Tehran University P.O. Box / Tehran IRAN |
| |
| Affiliation: | Caro Lucas Electrical Engineering Department,Tehran University,P.O. Box 14155/6181,Tehran IRAN |
| |
| Abstract: | The purpose of this paper is to present a unified theory of several differentneural networks that have been proposed for solving various computation, pattern recog-nition, imaging, optimization, and other problems. The functioning of these networks ischaracterized by Lyapunov energy functions. The relationship between the deterministicand stochastic neural networks is examined. The simulated annealing methods for findingthe global optimum of an objective function as well as their generalization by injectingnoise into deterministic neural networks are discussed. A statistical interpretation of thedynamic evolution of the different neural networks is presented. The problem of trainingdifferent neural networks is investigated in this general framework. It is shown how thisapproach can be used not only for analyzing various neural networks, but also for the choiceof the proper neural network for solving any given problem and the design of a trainingalgorithm for the particular neural network. |
| |
| Keywords: | Neural networks stochastic systems information energy entropy |
| 本文献已被 CNKI 等数据库收录！ |
