| A MODEL OF NEURAL CIRCUIT WITH ADAPTION AND NONLINEAR CONNECTION |
| |
| 引用本文： | 冯大政. A MODEL OF NEURAL CIRCUIT WITH ADAPTION AND NONLINEAR CONNECTION[J]. 电子科学学刊(英文版), 1994, 11(3): 193-200. DOI: 10.1007/BF02684825 |
| |
| 作者姓名： | 冯大政 |
| |
| 作者单位： | Electronic Engineering |
| |
| 摘 要： | Based on physiological properties of synapse, soma and axon, this paper presents and analyses a model of neural circuit which can approximately simulate input-output relation, strength-duration curve, adaption and nonlinear connection of real neuron. The obtained results show that the model approximates to realistic principles of neural computation better than the available neural networks. The impulse-coded WTA(winner takes all) networks constructed with the above model find the winner more effectively than the analog WTA. Finally, the two important concepts: time competition and strength competition are introduced, which illustrate that the model has abilities to perform series and parallel information processing.
|
A model of neural circuit with adaption and nonlinear connection |
| |
| Feng Dazheng. A model of neural circuit with adaption and nonlinear connection[J]. Journal of Electronics, 1994, 11(3): 193-200. DOI: 10.1007/BF02684825 |
| |
| Authors: | Feng Dazheng |
| |
| Affiliation: | (1) Electronic Engineering Institute, Xidian University, 710071 Xi’an |
| |
| Abstract: | Based on physiological properties of synapse, soma and axon, this paper presents and analyses a model of neural circuit which can approximately simulate input-output relation, strength-duration curve, adaption and nonlinear connection of real neuron. The obtained results show that the model approximates to realistic principles of neural computation better than the available neural networks. The impulse-coded WTA(winner takes all) networks constructed with the above model find the winner more effectively than the analog WTA. Finally, the two important concepts: time competition and strength competition are introduced, which illustrate that the model has abilities to perform series and parallel information processing. |
| |
| Keywords: | Artificial neural net Nonlinear connection Adaption Property analysis Competition |
| 本文献已被 CNKI SpringerLink 等数据库收录！ |
| 点击此处可从《电子科学学刊(英文版)》浏览原始摘要信息 |
|
点击此处可从《电子科学学刊(英文版)》下载全文 |
