3 papers
cs.SE2025
Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networks
Sigma Jahan, Saurabh Singh Rajput, Tushar Sharma +1
Attention mechanisms are at the core of modern neural architectures, powering systems ranging from ChatGPT to autonomous vehicles and driving a major economic impact. However, high…
cs.LG2025
Can Hessian-Based Insights Support Fault Diagnosis in Attention-based Models?
Sigma Jahan, Mohammad Masudur Rahman
As attention-based deep learning models scale in size and complexity, diagnosing their faults becomes increasingly challenging. In this work, we conduct an empirical study to evalu…
cs.SE2025
Improved Detection and Diagnosis of Faults in Deep Neural Networks Using Hierarchical and Explainable Classification
Sigma Jahan, Mehil B Shah, Parvez Mahbub +1
Deep Neural Networks (DNN) have found numerous applications in various domains, including fraud detection, medical diagnosis, facial recognition, and autonomous driving. However, D…