Cellular Automata are discrete dynamical systems that evolve following simpleand local rules. Despite of its local simplicity, knowledge discovery in CA isa NP problem. This is the main motivation for using data mining techniques forCA study. The Principal Component Analysis (PCA) is a useful tool for datamining because it provides a compact and optimal description of data sets. Suchfeature have been explored to compute the best subspace which maximizes theprojection of the I/O patterns of CA onto the principal axis. The stability ofthe principal components against the input patterns is the main result of thisapproach. In this paper we perform such analysis but in the presence of noisewhich randomly reverses the CA output values with probability $p$. As expected,the number of principal components increases when the pattern size isincreased. However, it seems to remain stable when the pattern size isunchanged but the noise intensity gets larger. We describe our experiments andpoint out further works using KL transform theory and parameter sensitivityanalysis.
展开▼
机译：元胞自动机是离散的动力系统，遵循简单和局部的规则发展。尽管它在本地很简单，但是CA中的知识发现还是一个NP问题。这是使用数据挖掘技术进行CA研究的主要动机。主成分分析（PCA）是用于数据挖掘的有用工具，因为它提供了对数据集的紧凑且最佳的描述。已经探索出这种功能来计算最佳子空间，该子空间可以最大程度地将CA的I / O模式投影到主轴上。主成分相对于输入模式的稳定性是该方法的主要结果。在本文中，我们执行了这种分析，但是在存在噪声的情况下，该噪声以概率$ p $随机反转了CA输出值。如预期的那样，当图案尺寸增加时，主成分的数量增加。但是，当图案大小不变但噪声强度变大时，它似乎保持稳定。我们描述了我们的实验，并指出了使用KL变换理论和参数敏感性分析的进一步工作。
展开▼
