论文标题
因果毯：理论和算法框架
Causal blankets: Theory and algorithmic framework
论文作者
论文摘要
我们介绍了一个新颖的框架，以根据计算力学原理直接从数据中识别感知行动回路（PALOS）。我们的方法基于因果毯的概念，该概念将感觉和主动变量捕获为动态的足够统计数据，即“有所不同的差异”。此外，我们的理论提供了一个广泛适用的程序来构建帕洛斯，既不需要稳态也不需要马尔可夫动力。利用我们的理论，我们表明，每个两部分随机过程都有因果笼罩，但是导致有效的帕洛公式的程度取决于两部分的综合信息。
We introduce a novel framework to identify perception-action loops (PALOs) directly from data based on the principles of computational mechanics. Our approach is based on the notion of causal blanket, which captures sensory and active variables as dynamical sufficient statistics -- i.e. as the "differences that make a difference." Moreover, our theory provides a broadly applicable procedure to construct PALOs that requires neither a steady-state nor Markovian dynamics. Using our theory, we show that every bipartite stochastic process has a causal blanket, but the extent to which this leads to an effective PALO formulation varies depending on the integrated information of the bipartition.
