| 多层神经网络的样本记忆能力 |
| |
| 引用本文： | 应行仁 曾南. 多层神经网络的样本记忆能力[J]. 计算机学报, 1992, 15(7): 536-540 |
| |
| 作者姓名： | 应行仁 曾南 |
| |
| 作者单位： | 中国科学院自动化研究所国家模式识别实验室，中国科学院自动化研究所国家模式识别实验室 北京 100080，北京 100080 |
| |
| 摘 要： | 本文论述了前馈型网络,隐节点层进行线性独立变换的能力.严格证明了Mirchandani等关于隐节点在输入空间划分出区域数的定理.给出多层前馈型神经网络采用单位阶跃和连续渐近激发函数两种情况下,实数值样本绝对记忆能力的两个定理.
|
| 关 键 词： | 神经网络 样本记忆能力 |
SAMPLE RECORDING ABILITY OF MULTI-LAYER NEURAL NETWORKS |
| |
| Ying Xingren and Zeng Nan. SAMPLE RECORDING ABILITY OF MULTI-LAYER NEURAL NETWORKS[J]. Chinese Journal of Computers, 1992, 15(7): 536-540 |
| |
| Authors: | Ying Xingren and Zeng Nan |
| |
| Abstract: | This paper mentions about the linearly independent transformation abilityof hidden layer in feed-forward nets. An exact, proof for Mirchandani's theorem which counts the regions of input space partitioned by the hidden nodes. Two theorems about real sample absolute recording ability corresponding with unit step and continuous asymptotic activation functions in multi-layer feed-forward neural networks, respectively, are provided. |
| |
| Keywords: | Neural networks artificial neural networks feed-forward nets capacity of networks sample recording ability. |
| 本文献已被 CNKI 维普 等数据库收录！ |
