14 citations · 25 across the 6 of their papers we have counts for
6 papers
Feature-level Interaction Explanations in Multimodal Transformers
Yeji Kim, Housam Khalifa Bashier Babiker, Mi-Young Kim +1
Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision. Most existing multimodal explainable AI (MXAI) methods ext…
Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations
Shahin Atakishiyev, Housam K. B. Babiker, Jiayi Dai +8
Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next…
Explaining Autonomous Driving Actions with Visual Question Answering
Shahin Atakishiyev, Mohammad Salameh, Housam Babiker +1
The end-to-end learning ability of self-driving vehicles has achieved significant milestones over the last decade owing to rapid advances in deep learning and computer vision algor…
A multi-component framework for the analysis and design of explainable artificial intelligence
S. Atakishiyev, H. Babiker, N. Farruque +6
The rapid growth of research in explainable artificial intelligence (XAI) follows on two substantial developments. First, the enormous application success of modern machine learnin…
An Introduction to Deep Visual Explanation
Housam Khalifa Bashier Babiker, Randy Goebel
The practical impact of deep learning on complex supervised learning problems has been significant, so much so that almost every Artificial Intelligence problem, or at least a port…
Using KL-divergence to focus Deep Visual Explanation
Housam Khalifa Bashier Babiker, Randy Goebel
We present a method for explaining the image classification predictions of deep convolution neural networks, by highlighting the pixels in the image which influence the final class…