Gradient Backpropagation based Feature Attribution to Enable Explainable-AI on the Edge

by   Ashwin Bhat, et al.

There has been a recent surge in the field of Explainable AI (XAI) which tackles the problem of providing insights into the behavior of black-box machine learning models. Within this field, feature attribution encompasses methods which assign relevance scores to input features and visualize them as a heatmap. Designing flexible accelerators for multiple such algorithms is challenging since the hardware mapping of these algorithms has not been studied yet. In this work, we first analyze the dataflow of gradient backpropagation based feature attribution algorithms to determine the resource overhead required over inference. The gradient computation is optimized to minimize the memory overhead. Second, we develop a High-Level Synthesis (HLS) based configurable FPGA design that is targeted for edge devices and supports three feature attribution algorithms. Tile based computation is employed to maximally use on-chip resources while adhering to the resource constraints. Representative CNNs are trained on CIFAR-10 dataset and implemented on multiple Xilinx FPGAs using 16-bit fixed-point precision demonstrating flexibility of our library. Finally, through efficient reuse of allocated hardware resources, our design methodology demonstrates a pathway to repurpose inference accelerators to support feature attribution with minimal overhead, thereby enabling real-time XAI on the edge.


page 1

page 2


Automatic Compiler Based FPGA Accelerator for CNN Training

Training of convolutional neural networks (CNNs)on embedded platforms to...

Bidding Through the Lens of Attribution: Pick the Right Labels!

Attribution-the mechanism that assigns conversion credits to individual ...

Achieving Transparency in Distributed Machine Learning with Explainable Data Collaboration

Transparency of Machine Learning models used for decision support in var...

Non-Uniform Interpolation in Integrated Gradients for Low-Latency Explainable-AI

There has been a surge in Explainable-AI (XAI) methods that provide insi...

Towards a Shapley Value Graph Framework for Medical peer-influence

eXplainable Artificial Intelligence (XAI) is a sub-field of Artificial I...

Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators

In this paper we present Hyper-Dimensional Reconfigurable Analytics at t...

Picasso, Matisse, or a Fake? Automated Analysis of Drawings at the Stroke Level for Attribution and Authentication

This paper proposes a computational approach for analysis of strokes in ...

Please sign up or login with your details

Forgot password? Click here to reset