Label-Critic Tsetlin Machine: A Novel Self-supervised Learning Scheme for Interpretable Clustering
Ahmed Abouzeid, Ole‐Christoffer Granmo, Morten Goodwin, Christian Webersik · 2022
Unlike typical machine learning algorithms such as Artificial Neural Networks, the Tsetlin Machine (TM) is based on propositional logic instead of arithmetic operations, promoting it as a novel machine learning paradigm with interpretable learning outcomes. To this end, this paper proposes a self-supervised learning scheme inspired by the self-correction and interpretability provided by a standard TM. The proposed architecture uses a twin of Label-Critic Tsetlin Automata (TAs). The Label-TA learns the individual samples’ correct labels guided by a self-corrected TM logical clause. At the same time, the Critic-TA validates the learning and approves the Label-TA reward. Our empirical results on synthetic and real data show promising capabilities for self-supervised learning and interpretable clustering. Furthermore, the Label-Critic TM architecture demonstrates how propositional logic-based learning provides self-correction with the absence of the ground truths in data.