# Hardware Acceleration of Explainable Machine Learning using Tensor Processing Units

arXiv: https://arxiv.org/abs/2103.11927 · HTML: https://mlsanity.com/paper/2103.11927/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks](https://mlsanity.com/paper/2102.10423/) (2021)
- [Turning Internet of Things(IoT) into Internet of Vulnerabilities (IoV) : IoT Botnets](https://mlsanity.com/paper/1702.03681/) (2017)
- [High Performance Monte Carlo Simulation of Ising Model on TPU Clusters](https://mlsanity.com/paper/1903.11714/) (2019)
- [Large-Scale Discrete Fourier Transform on TPUs](https://mlsanity.com/paper/2002.03260/) (2020)
- [Accelerating MRI Reconstruction on TPUs](https://mlsanity.com/paper/2006.14080/) (2020)

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

- [Gradient Backpropagation based Feature Attribution to Enable Explainable-AI on the Edge](https://mlsanity.com/paper/2210.10922/) (2022)
- [Non-Uniform Interpolation in Integrated Gradients for Low-Latency Explainable-AI](https://mlsanity.com/paper/2302.11107/) (2023)
- [Explainable AI for Embedded Systems Design: A Case Study of Static Redundant NVM Memory Write Prediction](https://mlsanity.com/paper/2403.04337/) (2024)
- [ApproXAI: Energy-Efficient Hardware Acceleration of Explainable AI using Approximate Computing](https://mlsanity.com/paper/2504.17929/) (2025)

## Abstract (arXiv)

Machine learning (ML) is successful in achieving human-level performance in various fields. However, it lacks the ability to explain an outcome due to its black-box nature. While existing explainable ML is promising, almost all of these methods focus on formatting interpretability as an optimization problem. Such a mapping leads to numerous iterations of time-consuming complex computations, which limits their applicability in real-time applications. In this paper, we propose a novel framework for accelerating explainable ML using Tensor Processing Units (TPUs). The proposed framework exploits the synergy between matrix convolution and Fourier transform, and takes full advantage of TPU's natural ability in accelerating matrix computations. Specifically, this paper makes three important contributions. (1) To the best of our knowledge, our proposed work is the first attempt in enabling hardware acceleration of explainable ML using TPUs. (2) Our proposed approach is applicable across a wide variety of ML algorithms, and effective utilization of TPU-based acceleration can lead to real-time outcome interpretation. (3) Extensive experimental results demonstrate that our proposed approach can provide an order-of-magnitude speedup in both classification time (25x on average) and interpretation time (13x on average) compared to state-of-the-art techniques.