110 citations · 165 across the 15 of their papers we have counts for
9 papers · 1 filter
Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation
Christopher Angelini, Nidhal Bouaynaya
When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, res…
Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning
Hikmat Khan, Ghulam Rasool, Nidhal Carla Bouaynaya
Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic f…
Variational Density Propagation Continual Learning
Christopher Angelini, Nidhal Bouaynaya, Ghulam Rasool
Deep Neural Networks (DNNs) deployed to the real world are regularly subject to out-of-distribution (OoD) data, various types of noise, and shifting conceptual objectives. This pap…
The Importance of Robust Features in Mitigating Catastrophic Forgetting
Hikmat Khan, Nidhal C. Bouaynaya, Ghulam Rasool
Continual learning (CL) is an approach to address catastrophic forgetting, which refers to forgetting previously learned knowledge by neural networks when trained on new tasks or d…
EvalAttAI: A Holistic Approach to Evaluating Attribution Maps in Robust and Non-Robust Models
Ian E. Nielsen, Ravi P. Ramachandran, Nidhal Bouaynaya +2
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 mode…
Robust Learning via Ensemble Density Propagation in Deep Neural Networks
Giuseppina Carannante, Dimah Dera, Ghulam Rasool +2
Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for…
Self-Compression in Bayesian Neural Networks
Giuseppina Carannante, Dimah Dera, Ghulam Rasool +1
Machine learning models have achieved human-level performance on various tasks. This success comes at a high cost of computation and storage overhead, which makes machine learning…
Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks
Ian E. Nielsen, Dimah Dera, Ghulam Rasool +2
With the rise of deep neural networks, the challenge of explaining the predictions of these networks has become increasingly recognized. While many methods for explaining the decis…
Exploring Robust Architectures for Deep Artificial Neural Networks
Asim Waqas, Ghulam Rasool, Hamza Farooq +1
The architectures of deep artificial neural networks (DANNs) are routinely studied to improve their predictive performance. However, the relationship between the architecture of a…