ADVANCED SUPERVISED LEARNING IN MULTILAYER PERCEPTRONS - FROM BACKPROPAGATION TO ADAPTIVE LEARNING ALGORITHMS
ADVANCED SUPERVISED LEARNING IN MULTILAYER PERCEPTRONS - FROM BACKPROPAGATION TO ADAPTIVE LEARNING ALGORITHMS
复制标题
DOI：
10.1016/0920-5489(94)90017-5
复制
发表时间：
1994-07-01
影响因子：
5
通讯作者：
RIEDMILLER, M
中科院分区：
文献类型：
--
作者：
RIEDMILLER, M
自从反向传播算法[1]提出以来，人们对前馈神经网络中的权值训练技术提出了各种各样的改进。介绍了基于梯度下降技术的多层感知器中监督学习的概念。讨论了原始反向传播学习过程中的一些问题和缺陷，最终导致了更复杂技术的发展。本文主要讨论自适应学习策略。根据全局自适应策略和局部自适应策略对一些最流行的学习算法进行了描述和讨论，并报告了几个学习过程在一些流行的基准问题上的行为，从而说明了各自算法的收敛、鲁棒性和伸缩性。
Since the presentation of the backpropagation algorithm [1] a vast variety of improvements of the technique for training the weights in a feed-forward neural network have been proposed. The following article introduces the concept of supervised learning in multi-layer perceptrons based on the technique of gradient descent. Some problems and drawbacks of the original backpropagation learning procedure are discussed, eventually leading to the development of more sophisticated techniques This article concentrates on adaptive learning strategies. Some of the most popular learning algorithms are described and discussed according to their classification in terms of global and local adaptation strategies.The behavior of several learning procedures on some popular benchmark problems is reported, thereby illuminating convergence, robustness, and scaling properties of the respective algorithms.