Causality Preserving Chaotic Transformation and Classification using Neurochaos Learning

0570030 - ÚI 2024 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Harikrishnan, N. B. - Kathpalia, Aditi - Nagaraj, N.
Causality Preserving Chaotic Transformation and Classification using Neurochaos Learning.
Advances in Neural Information Processing Systems 35 (NeurIPS 2022). New Orleans: Curran Associates, 2022 - (Koyejo, S.; Mohamed, S.; Agarwal, A.; Belgrave, D.; Cho, K.; Oh, A.), č. článku 189185. ISBN 978-171387108-8. ISSN 1049-5258.
[NeurIPS 2022: Conference on Neural Information Processing Systems /36./. New Orleans / virtual (US), 28.11.2022-09.12.2022]
Grant CEP: GA ČR(CZ) GA19-16066S
Grant ostatní: AV ČR(CZ) AP1901
Program: Akademická prémie - Praemium Academiae
Institucionální podpora: RVO:67985807
Klíčová slova: neurochaos learning * cause-effect classification * transfer learning * causal machine learning
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
https://proceedings.neurips.cc/paper_files/paper/2022/file/0d9057d84a9fc37523bf826232ea6820-Paper-Conference.pdf

Discovering cause and effect variables from observational data is an important but challenging problem in science and engineering. In this work, a recently proposed brain inspired learning algorithm namely-Neurochaos Learning (NL) is used for the classification of cause and effect time series generated using coupled autoregressive processes, coupled 1D chaotic skew tent maps, coupled 1D chaotic logistic maps and a real-world prey-predator system. In the case of coupled skew tent maps, the proposed method consistently outperforms a five layer Deep Neural Network (DNN) and Long Short Term Memory (LSTM) architecture for unidirectional 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 for coupled autoregressive processes and Compression-Complexity Causality for coupled chaotic systems and real-world prey-predator dataset. Unlike DNN, LSTM and 1D Convolutional Neural Network, it is found that NL preserves the inherent causal structures present in the input timeseries data. These findings are promising for the theory and applications of causal machine learning and open up the possibility to explore the potential of NL for more sophisticated causal learning tasks.
Trvalý link: https://hdl.handle.net/11104/0341401