期刊
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT III
卷 11141, 期 -, 页码 564-573出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-01424-7_55
关键词
-
Concerned with neural learning without backpropagation, we investigate variants of the simultaneous perturbation stochastic approximation (SPSA) algorithm. Experimental results suggest that these allow for the successful training of deep feed-forward neural networks using forward passes only. In particular, we find that SPSA-based algorithms which update network parameters in a layer-wise manner are superior to variants which update all weights simultaneously.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据