Trustworthy Tree-based Machine Learning by MoS2 Flash-based Analog CAM with Inherent Soft Boundaries
Preprint
- 12 June 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
The rapid advancement of artificial intelligence has raised concerns regarding its trustworthiness, especially in terms of interpretability and robustness. Tree-based models like Random Forest and XGBoost excel in interpretability and accuracy for tabular data, but scaling them remains computationally expensive due to poor data locality and high data dependence. Previous efforts to accelerate these models with analog content addressable memory (CAM) have struggled, due to the fact that the difficult-to-implement sharp decision boundaries are highly susceptible to device variations, which leads to poor hardware performance and vulnerability to adversarial attacks. This work presents a novel hardware-software co-design approach using MoS 2 Flash-based analog CAM with inherent soft boundaries, enabling efficient inference with soft tree-based models. Our soft tree model inference experiments on MoS 2 analog CAM arrays show this method achieves exceptional robustness against device variation and adversarial attacks while achieving state-of-the-art accuracy. Specifically, our fabricated analog CAM arrays achieve 97% accuracy on the Iris dataset, while our experimentally calibrated model shows only a 0.6% accuracy drop on the MNIST dataset under 10% device threshold variation, compared to a 45.3% drop for traditional decision trees. This work paves the way for specialized hardware that enhances AI’s trustworthiness and efficiency.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- Tabular data: Deep learning is not all you needInformation Fusion, 2022
- Explainable artificial intelligence (XAI) post-hoc explainability methods: risks and limitations in non-discrimination lawAI and Ethics, 2022
- The three ghosts of medical AI: Can the black-box present deliver?Artificial Intelligence in Medicine, 2022
- The Road for 2D Semiconductors in the Silicon AgeAdvanced Materials, 2021
- Tree-based machine learning performed in-memory with memristive analog CAMNature Communications, 2021
- Transparency and the Black Box Problem: Why We Do Not Trust AIPhilosophy & Technology, 2021
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020
- Analog content-addressable memories with memristorsNature Communications, 2020
- Challenges hindering memristive neuromorphic hardware from going mainstreamNature Communications, 2018
- High-mobility and low-power thin-film transistors based on multilayer MoS2 crystalsNature Communications, 2012