no code implementations • 29 Oct 2023 • Tianhao Zhang, Shenglin Wang, Nidhal Bouaynaya, Radu Calinescu, Lyudmila Mihaylova
The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data.
no code implementations • 22 Aug 2023 • Christopher Angelini, Nidhal Bouaynaya, Ghulam Rasool
Catastrophic forgetting is mitigated by using the closed-form ELBO to approximate the Minimum Description Length (MDL) Principle, inherently penalizing changes in the model likelihood by minimizing the KL Divergence between the variational posterior for the current task and the previous task's variational posterior acting as the prior.
no code implementations • 15 Mar 2023 • Ian E. Nielsen, Ravi P. Ramachandran, Nidhal Bouaynaya, Hassan M. Fathallah-Shaykh, Ghulam Rasool
The expansion of explainable artificial intelligence as a field of research has generated numerous methods of visualizing and understanding the black box of a machine learning model.
no code implementations • 23 Jul 2021 • Ian E. Nielsen, Dimah Dera, Ghulam Rasool, Nidhal Bouaynaya, Ravi P. Ramachandran
Later, we discuss how gradient-based methods can be evaluated for their robustness and the role that adversarial robustness plays in having meaningful explanations.