Randomness in generalization ability: a source to improve it
Randomness in generalization ability: a source to improve it
复制标题
泛化能力的随机性：提高泛化能力的来源
DOI：
10.1109/72.501725
复制
发表时间：
1996
期刊：
影响因子：
--
通讯作者：
D. Sarkar
中科院分区：
文献类型：
--
作者：
D. Sarkar
在神经元及其互连的几种模型中，前馈人工神经网络（FFANN）因其简单性和有效性而最受欢迎。诸如学习时间长和局部最小值之类的困难可能不会像泛化能力问题那样影响FFANN，因为一个网络只需要一次训练，然后就可以使用很长时间。本文报告了我们对 FFANN 泛化能力随机性的观察。定义了一种测量泛化能力的新方法。该方法可用于识别学习系统泛化能力的随机程度。如果 FFANN 架构在给定问题的泛化能力上表现出随机性，则可以使用多个网络来改进它。我们开发了一个模型，称为投票模型，用于预测多个网络的泛化能力。研究表明，如果单个网络的正确分类概率大于一半，那么随着投票网络中网络数量的增加，其泛化能力也会随之增加。进一步分析表明，随着投票网络中网络数量的增加，投票网络模型的VC维数可能单调增加。
Among several models of neurons and their interconnections, feedforward artificial neural networks (FFANNs) are most popular, because of their simplicity and effectiveness. Difficulties such as long learning time and local minima may not affect FFANNs as much as the question of generalization ability, because a network needs only one training, and then it may be used for a long time. This paper reports our observations about randomness in generalization ability of FFANNs. A novel method for measuring generalization ability is defined. This method can be used to identify degree of randomness in generalization ability of learning systems. If an FFANN architecture shows randomness in generalization ability for a given problem, multiple networks can be used to improve it. We have developed a model, called voting model, for predicting generalization ability of multiple networks. It has been shown that if correct classification probability of a single network is greater than half, then as the number of networks in a voting network is increased so does its generalization ability. Further analysis has shown that VC-dimension of the voting network model may increase monotonically as the number of networks in the voting networks is increased.