HIDDEN INFORMATION MAXIMIZATION FOR FEATURE DETECTION AND RULE DISCOVERY
HIDDEN INFORMATION MAXIMIZATION FOR FEATURE DETECTION AND RULE DISCOVERY
复制标题
用于特征检测和规则发现的隐藏信息最大化
DOI：
10.1088/0954-898x_6_4_004
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
S. Nakanishi
中科院分区：
文献类型：
--
作者：
R. Kamimura;S. Nakanishi
本文提出了一种最大化隐藏单元中隐藏信息的方法。隐藏的信息被定义为隐藏单元相对于输入模式的不确定性的减少。通过最大化隐藏信息，隐藏单元可以检测输入模式背后的特征并提取规则。我们的方法被应用到两个问题：一个自动编码器产生六个字母和同化形成的复数和鼻音在人工语言。在第一个问题中，结果明确地证实了输入模式的特征可以通过最大化隐藏信息来检测。在第二个实验中，我们可以清楚地看到，同化的规则是通过最大化隐藏信息来提取的，即使规则被其他因素掩盖。
In this paper, We propose a method to maximize the hidden information stored in hidden units. The hidden information is defined by the decrease in uncertainty of hidden units with respect to input patterns. By maximizing the hidden information, the hidden unit can detect features and extract rules behind input patterns. Our method was applied to two problems: an autoencoder to produce six alphabet letters and the assimilation for the formation of plurals and nasalization in an artificial language. In the first problem, the results explicitly confirmed that the features of input patterns could be detected by maximizing the hidden information. In the second experiment, we could clearly see that the rules of the assimilation were extracted by maximizing the hidden information, even if the rules are obscured by some other factors.