Convergence of learning algorithms with constant learning rates
Convergence of learning algorithms with constant learning rates
复制标题
具有恒定学习率的学习算法的收敛
DOI：
--
复制
发表时间：
1991
期刊：
影响因子：
--
通讯作者：
K. Hornik
中科院分区：
文献类型：
--
作者：
Chung;K. Hornik
研究了具有恒定学习率的神经网络学习算法在平稳随机输入环境中的行为。在随机过程趋于零的弱收敛意义上，严格地证明了权估计序列可以用一个常微分方程来近似。作为应用，本文对前馈结构中的反向传播和一些特征提取算法进行了较为详细的研究。
The behavior of neural network learning algorithms with a small, constant learning rate, epsilon, in stationary, random input environments is investigated. It is rigorously established that the sequence of weight estimates can be approximated by a certain ordinary differential equation, in the sense of weak convergence of random processes as epsilon tends to zero. As applications, backpropagation in feedforward architectures and some feature extraction algorithms are studied in more detail.