Search Results for author:
Found 2 papers, 0 papers with code
Non-Uniform Interpolation in Integrated Gradients for Low-Latency Explainable-AI
Integrated Gradients (IG) is a popular XAI algorithm that attributes relevance scores to input features commensurate with their contribution to the model's output.
Gradient Backpropagation based Feature Attribution to Enable Explainable-AI on the Edge
In this work, we first analyze the dataflow of gradient backpropagation based feature attribution algorithms to determine the resource overhead required over inference.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
