Cause-Effect Preservation and Classification using Neurochaos Learning
This addresses the challenge of causal discovery in science and engineering, offering a method that preserves causality under chaotic transformations, though it appears incremental as it builds on existing Neurochaos Learning.
The paper tackled the problem of classifying cause-effect relationships from observational data using Neurochaos Learning, achieving consistent outperformance over a five-layer Deep Neural Network across various simulated and real-world datasets, with coupling coefficients from 0.1 to 0.7.
Discovering cause-effect from observational data is an important but challenging problem in science and engineering. In this work, a recently proposed brain inspired learning algorithm namely-\emph{Neurochaos Learning} (NL) is used for the classification of cause-effect from simulated data. The data instances used are generated from coupled AR processes, coupled 1D chaotic skew tent maps, coupled 1D chaotic logistic maps and a real-world prey-predator system. The proposed method consistently outperforms a five layer Deep Neural Network architecture for coupling coefficient values ranging from $0.1$ to $0.7$. Further, we investigate the preservation of causality in the feature extracted space of NL using Granger Causality (GC) for coupled AR processes and and Compression-Complexity Causality (CCC) for coupled chaotic systems and real-world prey-predator dataset. This ability of NL to preserve causality under a chaotic transformation and successfully classify cause and effect time series (including a transfer learning scenario) is highly desirable in causal machine learning applications.