Integrating Causality with Neurochaos Learning: Proposed Approach and Research Agenda
Nanjangud C. Narendra, Nithin Nagaraj
TL;DR
The paper addresses limitations of deep learning—namely reliance on statistical correlations and high energy consumption—by proposing a framework that integrates causality with Neurochaos Learning (NL) for graph-structured data. It develops a causality–NL integration via graph neural networks, including a mindmap and a survey of CLGNN approaches, with a strawman for NL integration into GNNs and numerous research questions guiding future work. Core contributions include conceptualizing Causality-NL fusion on SCMs and knowledge graphs, outlining extensions to predictive modeling and reinforcement learning, and highlighting ontology-driven enrichment through causal knowledge graphs. The proposed direction aims to improve accuracy, data efficiency, and robustness in domains with linked data (e.g., IoT, healthcare) by leveraging brain-inspired NL alongside principled causal reasoning. The work lays out a comprehensive agenda to operationalize causality-NL integration across classification, prediction, and control tasks.
Abstract
Deep learning implemented via neural networks, has revolutionized machine learning by providing methods for complex tasks such as object detection/classification and prediction. However, architectures based on deep neural networks have started to yield diminishing returns, primarily due to their statistical nature and inability to capture causal structure in the training data. Another issue with deep learning is its high energy consumption, which is not that desirable from a sustainability perspective. Therefore, alternative approaches are being considered to address these issues, both of which are inspired by the functioning of the human brain. One approach is causal learning, which takes into account causality among the items in the dataset on which the neural network is trained. It is expected that this will help minimize the spurious correlations that are prevalent in the learned representations of deep neural networks. The other approach is Neurochaos Learning, a recent development, which draws its inspiration from the nonlinear chaotic firing intrinsic to neurons in biological neural networks (brain/central nervous system). Both approaches have shown improved results over just deep learning alone. To that end, in this position paper, we investigate how causal and neurochaos learning approaches can be integrated together to produce better results, especially in domains that contain linked data. We propose an approach for this integration to enhance classification, prediction and reinforcement learning. We also propose a set of research questions that need to be investigated in order to make this integration a reality.