Related papers: Reactive Model Correction: Mitigating Harm to Task…
In practice, reinforcement learning (RL) agents are often trained with a possibly imperfect proxy reward function, which may lead to a human-agent alignment issue (i.e., the learned policy either converges to non-optimal performance with…
A deraining network can be interpreted as a conditional generator that aims at removing rain streaks from image. Most existing image deraining methods ignore model errors caused by uncertainty that reduces embedding quality. Unlike existing…
Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…
Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network layers in parallel and fully leveraging the computing…
Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a…
The Hessian spectrum of trained deep networks exhibits a characteristic structure: a continuous bulk of near-zero eigenvalues and a small number of large outlier eigenvalues (spikes), confirming the relevance of Random Matrix Theory in deep…
Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the difficulty of the inputs. In this way, the model can adjust…
Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. However, co-occurrence bias in the training dataset may hamper a DNN model's generalizability to unseen scenarios…
The paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed, and a step-by-step framework on how to detect and test bias is introduced. Since…
Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more effective attention based on causal inference. Unlike most…
Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical…
Explainable Artificial Intelligence (XAI) emerged to reveal the internal mechanism of machine learning models and how the features affect the prediction outcome. Collinearity is one of the big issues that XAI methods face when identifying…
Model learning from class imbalanced training data is a long-standing and significant challenge for machine learning. In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in…
Medical events of interest, such as mortality, often happen at a low rate in electronic medical records, as most admitted patients survive. Training models with this imbalance rate (class density discrepancy) may lead to suboptimal…
Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier. A challenge is to identify which points to label to best improve performance…
Deep Reinforcement Learning (DRL) has become a powerful methodology to solve complex decision-making problems. However, DRL has several limitations when used in real-world problems (e.g., robotics applications). For instance, long training…
Recent years have witnessed the great success of convolutional neural network (CNN) based models in the field of computer vision. CNN is able to learn hierarchically abstracted features from images in an end-to-end training manner. However,…
We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on…
Ensuring both transparency and safety is critical when deploying Deep Neural Networks (DNNs) in high-risk applications, such as medicine. The field of explainable AI (XAI) has proposed various methods to comprehend the decision-making…
Reinforcement learning is an appropriate and successful method to robustly perform low-level robot control under noisy conditions. Symbolic action planning is useful to resolve causal dependencies and to break a causally complex problem…