English

Self-timed Reinforcement Learning using Tsetlin Machine

Signal Processing 2021-09-03 v1 Machine Learning

Abstract

We present a hardware design for the learning datapath of the Tsetlin machine algorithm, along with a latency analysis of the inference datapath. In order to generate a low energy hardware which is suitable for pervasive artificial intelligence applications, we use a mixture of asynchronous design techniques - including Petri nets, signal transition graphs, dual-rail and bundled-data. The work builds on previous design of the inference hardware, and includes an in-depth breakdown of the automaton feedback, probability generation and Tsetlin automata. Results illustrate the advantages of asynchronous design in applications such as personalized healthcare and battery-powered internet of things devices, where energy is limited and latency is an important figure of merit. Challenges of static timing analysis in asynchronous circuits are also addressed.

Keywords

Cite

@article{arxiv.2109.00846,
  title  = {Self-timed Reinforcement Learning using Tsetlin Machine},
  author = {Adrian Wheeldon and Alex Yakovlev and Rishad Shafik},
  journal= {arXiv preprint arXiv:2109.00846},
  year   = {2021}
}
R2 v1 2026-06-24T05:37:26.175Z