<ul><li>The Tsetlin Machine (TM) is a propositional logic based model that uses conjunctive clauses to learn patterns from data.</li><li>A novel approach to implementing knowledge distillation in Tsetlin Machines is proposed.</li><li>Utilizing probability distributions of each output sample in the teacher provides additional context to the student model.</li><li>The proposed algorithm improves the performance of the student model without negatively impacting latency in image recognition and text classification.</li></ul>

A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machines

Discover more