Neural network information criterion for the optimal number of hidden units
Neural network information criterion for the optimal number of hidden units
复制标题
最佳隐藏单元数量的神经网络信息准则
DOI：
10.1109/icnn.1995.488108
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
T. Onoda
中科院分区：
文献类型：
--
作者：
T. Onoda
本文提出了一种统计方法来解决人工神经网络模型选择问题，或确定隐藏单元的数量。作者的方法分析了学习误差与一般泛化误差之间的关系，学习误差是收敛性的度量，泛化误差是由统计差异和学习算法伴随的差异来衡量近似质量。通过对两种误差的统计分析，明确了学习误差与泛化误差之间的关系。在此基础上，推导出一个基于给定学习集的信息准则。作者将此信息准则称为“神经网络信息准则：NNIC”。利用该准则可以构造给定学习实例的多层神经网络的最优结构。通过对NNIC和NIC的简单仿真，证明了该准则的有效性。最后，作者指出NNIC是一些信息准则的广义形式。
This paper presents a statistical approach to solve the problem of model selection, or determine the number of hidden units for artificial neural networks. The authors' approach analyzes the relation between the learning error which is a measure of the convergence and the general generalization error which is a measure of the quality of approximation by a statistical discrepancy and a discrepancy accompanied by the learning algorithm. The author makes clear the relation between the learning error and the generalization error by analyzing the two discrepancies statistically. Moreover, the author derives a new information criterion based on a given learning set by this relation. The author calls this information criterion a "neural network information criterion: NNIC". The author can construct the optimal architecture of multi-layered neural networks for given learning examples by using this criterion. This paper shows that this criterion is effective by a simple simulation which compares NNIC with NIC. Finally, the author points out that NNIC is the generalized form of some information criteria.