| 摘要: |
| 文章指出了随机神经网络em学习算法仍然存在着收敛于局部极小值之缺陷.针对三层随机感知机,文章将em学习算法与Solis和Wets的随机优化算法结合起来,提出了三层随机感知机的混合型新学习算法HRem.文章从理论的角度证明了混合型新学习算法HRem能以概率1全局收敛于随机感知机的基于Kullback-Leibler差异度量的最小值.这一理论结果对em学习算法的深入研究有重要意义. |
| 关键词: 随机神经网络，em学习算法，随机优化算法. |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国家自然科学基金和江苏省跨世纪学术带头人基金资助. |
|
| The Hybrid Learning Algorithm Which is Based on em Algorithm and can Globally Converge with Probability 1 |
|
WANG Shi-tong
|
| Abstract: |
| In this paper, the drawback is pointed out that the learning algorithm em of random neural network sometimes converges to local minimum. A new hybrid learning algorithm HRem, which combines algorithm em and the random optimization algorithm presented by Dr. Solis and Wets, is presented for 3-layer random perception. It is theoretically proved that algorithm HRem can globally converge to the minimum of Kullback-Leibler difference measure. This theoretical result has important significances for further research on algorithm em. |
| Key words: Random neural networks, em learning algorithm, random optimization algorithm. |
