# TMComposites: Plug-and-Play Collaboration Between Specialized Tsetlin Machines

arXiv: https://arxiv.org/abs/2309.04801 · HTML: https://mlsanity.com/paper/2309.04801/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 9 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Counterfactual Generative Networks](https://mlsanity.com/paper/2101.06046/) (2021)
- [The Tsetlin Machine -- A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic](https://mlsanity.com/paper/1804.01508/) (2018)
- [The Convolutional Tsetlin Machine](https://mlsanity.com/paper/1905.09688/) (2019)
- [Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretability](https://mlsanity.com/paper/2005.05131/) (2020)
- [Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size](https://mlsanity.com/paper/2301.08190/) (2023)
- [A Relational Tsetlin Machine with Applications to Natural Language Understanding](https://mlsanity.com/paper/2102.10952/) (2021)

## Built on by (most cited first, 4 of 4)

- [An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites](https://mlsanity.com/paper/2406.00704/) (2024)
- [An All-digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification Accelerator](https://mlsanity.com/paper/2501.19347/) (2025)
- [Dynamic Tsetlin Machine Accelerators for On-Chip Training at the Edge using FPGAs](https://mlsanity.com/paper/2504.19797/) (2025)
- [Autonomous Collaborative Learning Among an Ensemble of Tsetlin Machines with Consensus-Based Inference](https://mlsanity.com/paper/2607.20124/) (2026)

## Abstract (arXiv)

Tsetlin Machines (TMs) provide a fundamental shift from arithmetic-based to logic-based machine learning. Supporting convolution, they deal successfully with image classification datasets like MNIST, Fashion-MNIST, and CIFAR-2. However, the TM struggles with getting state-of-the-art performance on CIFAR-10 and CIFAR-100, representing more complex tasks. This paper introduces plug-and-play collaboration between specialized TMs, referred to as TM Composites. The collaboration relies on a TM's ability to specialize during learning and to assess its competence during inference. When teaming up, the most confident TMs make the decisions, relieving the uncertain ones. In this manner, a TM Composite becomes more competent than its members, benefiting from their specializations. The collaboration is plug-and-play in that members can be combined in any way, at any time, without fine-tuning. We implement three TM specializations in our empirical evaluation: Histogram of Gradients, Adaptive Gaussian Thresholding, and Color Thermometers. The resulting TM Composite increases accuracy on Fashion-MNIST by two percentage points, CIFAR-10 by twelve points, and CIFAR-100 by nine points, yielding new state-of-the-art results for TMs. Overall, we envision that TM Composites will enable an ultra-low energy and transparent alternative to state-of-the-art deep learning on more tasks and datasets.