Neural network architectures and learning
Neural network architectures and learning
复制标题
神经网络架构和学习
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
B. Wilamowski
中科院分区：
文献类型：
--
作者：
B. Wilamowski
介绍了神经网络的各种学习方法，包括有监督和无监督的方法，并举例说明。一般的学习规则作为传入信号的函数进行了讨论。其他学习规则，如赫布学习，感知器学习，LMS（最小均方）学习，增量学习，WTA（赢家通吃）学习，和PCA（主成分分析）作为一般学习规则的推导。描述了级联相关网络、Sarajedini和Hecht-Nielsen网络、函数链接网络、多项式网络、对向传播网络、径向基函数（Radial Basis Function）网络的特定于架构的学习算法。专用的学习算法片上神经网络训练也进行了评估。本教程侧重于各种实用的方法，如Quickprop，RPROP，反渗透，三角洲酒吧三角洲等。分析了收敛困难的主要原因，如局部极小值或平斑问题。并举例说明了伪逆学习、共轭梯度法、牛顿法和LM（Levenberg-Marquardt）算法等更先进的梯度法。
Various learning methods of neural networks including supervised and unsupervised methods are presented and illustrated with examples. General learning rule as a function of the incoming signals is discussed. Other learning rules such as Hebbian learning, perceptron learning, LMS (least mean square) learning, delta learning, WTA (winner take all) learning, and PCA (principal component analysis) are presented as a derivation of the general learning rule. Architecture specific learning algorithms for cascade correlation networks, Sarajedini and Hecht-Nielsen networks, functional link networks, polynomial networks, counterpropagation networks, RBF (radial basis function) networks are described. Dedicated learning algorithms for on chip neural network training are also evaluated. The tutorial focuses on various practical methods such as Quickprop, RPROP, Back Percolation, Delta-bar-Delta and others. Main reasons of convergence difficulties such as local minima or flat spot problems are analyzed. More advance gradient-based methods including pseudo inversion learning, conjugate gradient, Newton and LM (Levenberg-Marquardt) algorithm are illustrated with examples.