Contracting Tsetlin Machine with Absorbing Automata

TL;DR

This paper presents a sparse Tsetlin Machine with absorbing automata that speeds up learning and reduces energy use by permanently including or excluding literals through absorbing states.

Contribution

It introduces a novel absorbing Tsetlin Automata mechanism that enhances the sparsity and efficiency of the Tsetlin Machine during learning.

Findings

Faster learning due to the sparse structure

Reduced energy consumption in training

Permanent inclusion/exclusion of literals

Abstract

In this paper, we introduce a sparse Tsetlin Machine (TM) with absorbing Tsetlin Automata (TA) states. In brief, the TA of each clause literal has both an absorbing Exclude- and an absorbing Include state, making the learning scheme absorbing instead of ergodic. When a TA reaches an absorbing state, it will never leave that state again. If the absorbing state is an Exclude state, both the automaton and the literal can be removed from further consideration. The literal will as a result never participates in that clause. If the absorbing state is an Include state, on the other hand, the literal is stored as a permanent part of the clause while the TA is discarded. A novel sparse data structure supports these updates by means of three action lists: Absorbed Include, Include, and Exclude. By updating these lists, the TM gets smaller and smaller as the literals and their TA withdraw. In this manner, the computation accelerates during learning, leading to faster learning and less energy consumption.