一种复合神经元网络结构的并行动力学及快速学习算法 |
| |
引用本文: | 王宝翰,岳刚.一种复合神经元网络结构的并行动力学及快速学习算法[J].生物物理学报,1992,8(1):165-173. |
| |
作者姓名: | 王宝翰 岳刚 |
| |
作者单位: | 中国科学院生物物理研究所,北京100101 |
| |
摘 要: | 提出两种功能互相不同的神经细胞组成的复合神经元网络(CNN)模型;导出一种特殊结构的CNN的并行动力学;而且证明了它的稳定性。在这些结果基础上,得到快速的假逆矩阵学习算法。计算机仿真试验证实学习算法与动力学稳定性的正确性,并表现出良好的容错性能与存储容量。
|
关 键 词: | 神经元网络 并行动力学 学习算法 |
PARALLEL DYNAMICS AND FAST LEARNING ALGORITHM FOR A COMPLEX NEURAL NETWORK |
| |
Abstract: | A complex neural network (CNN) , which consists of two types of nerve cell, differing functionally from each other, is suggested. Parallel dynamics for a special architecture of CNN is derived and its stability is proved. Based on the above-mentioned result, a fast pseudo-inverse matrix learning algorithm is obtained for the CNN. The validity of the learning algorithm and the dynamical stability are confirmed by the computer simulated experiments. |
| |
Keywords: | Neural network Parallel dynamics learning algorithm |
本文献已被 维普 等数据库收录! |
| 点击此处可从《生物物理学报》浏览原始摘要信息 |
| 点击此处可从《生物物理学报》下载免费的PDF全文 |
|