# Hardware Acceleration of Explainable Artificial Intelligence

arXiv: https://arxiv.org/abs/2305.04887 · HTML: https://mlsanity.com/paper/2305.04887/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 4 May 2023.

## Builds on (most cited first, 18 of 18)

- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [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)
- [Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution](https://mlsanity.com/paper/2004.10484/) (2020)
- [GPUTreeShap: Massively Parallel Exact Calculation of SHAP Scores for Tree Ensembles](https://mlsanity.com/paper/2010.13972/) (2020)
- [What does a network layer hear? Analyzing hidden representations of end-to-end ASR through speech synthesis](https://mlsanity.com/paper/1911.01102/) (2019)
- [Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA](https://mlsanity.com/paper/2203.05095/) (2022)
- [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)
- [Gradient Backpropagation based Feature Attribution to Enable Explainable-AI on the Edge](https://mlsanity.com/paper/2210.10922/) (2022)
- [Accelerating MRI Reconstruction on TPUs](https://mlsanity.com/paper/2006.14080/) (2020)

## Abstract (arXiv)

Machine learning (ML) is successful in achieving human-level artificial intelligence in various fields. However, it lacks the ability to explain an outcome due to its black-box nature. While recent efforts on explainable AI (XAI) has received significant attention, most of the existing solutions are not applicable in real-time systems since they map interpretability as an optimization problem, which leads to numerous iterations of time-consuming complex computations. Although there are existing hardware-based acceleration framework for XAI, they are implemented through FPGA and designed for specific tasks, leading to expensive cost and lack of flexibility. In this paper, we propose a simple yet efficient framework to accelerate various XAI algorithms with existing hardware accelerators. Specifically, this paper makes three important contributions. (1) The proposed method is the first attempt in exploring the effectiveness of Tensor Processing Unit (TPU) to accelerate XAI. (2) Our proposed solution explores the close relationship between several existing XAI algorithms with matrix computations, and exploits the synergy between convolution and Fourier transform, which takes full advantage of TPU's inherent ability in accelerating matrix computations. (3) Our proposed approach can lead to real-time outcome interpretation. Extensive experimental evaluation demonstrates that proposed approach deployed on TPU can provide drastic improvement in interpretation time (39x on average) as well as energy efficiency (69x on average) compared to existing acceleration techniques.