Advanced controls on energy reliability, flexibility, resilience, and occupant-centric control for smart and energy-efficient buildings—a state-of-the-art review
Advanced controls have attracted increasing interests due to the high requirement on smart
and energy-efficient (SEE) buildings and decarbonization in the building industry with …
and energy-efficient (SEE) buildings and decarbonization in the building industry with …
Trustworthy AI: From principles to practices
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment
of various systems based on it. However, many current AI systems are found vulnerable to …
of various systems based on it. However, many current AI systems are found vulnerable to …
[HTML][HTML] Information fusion as an integrative cross-cutting enabler to achieve robust, explainable, and trustworthy medical artificial intelligence
Medical artificial intelligence (AI) systems have been remarkably successful, even
outperforming human performance at certain tasks. There is no doubt that AI is important to …
outperforming human performance at certain tasks. There is no doubt that AI is important to …
Model complexity of deep learning: A survey
Abstract Model complexity is a fundamental problem in deep learning. In this paper, we
conduct a systematic overview of the latest studies on model complexity in deep learning …
conduct a systematic overview of the latest studies on model complexity in deep learning …
Smart: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization
Transfer learning has fundamentally changed the landscape of natural language processing
(NLP) research. Many existing state-of-the-art models are first pre-trained on a large text …
(NLP) research. Many existing state-of-the-art models are first pre-trained on a large text …
Freelb: Enhanced adversarial training for natural language understanding
Adversarial training, which minimizes the maximal risk for label-preserving input
perturbations, has proved to be effective for improving the generalization of language …
perturbations, has proved to be effective for improving the generalization of language …
A review of single-source deep unsupervised visual domain adaptation
Large-scale labeled training datasets have enabled deep neural networks to excel across a
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …
wide range of benchmark vision tasks. However, in many applications, it is prohibitively …
Robustness may be at odds with accuracy
We show that there may exist an inherent tension between the goal of adversarial
robustness and that of standard generalization. Specifically, training robust models may not …
robustness and that of standard generalization. Specifically, training robust models may not …
How does mixup help with robustness and generalization?
Mixup is a popular data augmentation technique based on taking convex combinations of
pairs of examples and their labels. This simple technique has been shown to substantially …
pairs of examples and their labels. This simple technique has been shown to substantially …
Robust reinforcement learning: A review of foundations and recent advances
Reinforcement learning (RL) has become a highly successful framework for learning in
Markov decision processes (MDP). Due to the adoption of RL in realistic and complex …
Markov decision processes (MDP). Due to the adoption of RL in realistic and complex …