160 citations · 246 across the 35 of their papers we have counts for
5 papers · 1 filter
Distributional Shifts in Automated Diabetic Retinopathy Screening
Jay Nandy, Wynne Hsu, Mong Li Lee
Deep learning-based models are developed to automatically detect if a retina image is `referable' in diabetic retinopathy (DR) screening. However, their classification accuracy deg…
Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
Feng Xie, Han Yuan, Yilin Ning +5
Objective: Temporal electronic health records (EHRs) can be a wealth of information for secondary uses, such as clinical events prediction or chronic disease management. However, c…
Towards Fully Interpretable Deep Neural Networks: Are We There Yet?
Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee
Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems. Research on opening black-box DN…
Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples
Jay Nandy, Sudipan Saha, Wynne Hsu +2
The current state-of-the-art defense methods against adversarial examples typically focus on improving either empirical or certified robustness. Among them, adversarially trained (…
Comprehensible Convolutional Neural Networks via Guided Concept Learning
Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee
Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the fe…