Deep Learning
The MAGICAL Benchmark for Robust Imitation
The robot could learn from these demonstrations to complete the tasks autonomously. For IL algorithms to be useful, however, they must be able to learn how to perform tasks from few demonstrations. A domestic robot wouldn't be very helpful if it required thirty demonstrations before it figured out that you are deliberately washing your purple cravat
Uncertainty Quantification and Deep Ensembles
Although the calibration of probabilistic models is well studied, calibrating extremely over-parametrized models in the low-data regime presents unique challenges.
Characterization of Excess Risk for Locally Strongly Convex Population Risk
The core problem in machine learning is obtaining a model that generalizes well on unseen test data. The excess risk decides the model's performance on these unseen data, and it can be decomposed
Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data
In mental state decoding, researchers aim to identify certain mental states (e.g., deciding to accept or
Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information Y ang Zhang
One principal approach for illuminating a black-box neural network is feature attribution, i.e. identifying the importance of input features for the network's prediction.
Masked Prediction: A Parameter Identifiability View
The vast majority of work in self-supervised learning have focused on assessing recovered features by a chosen set of downstream tasks.
Masked Prediction: A Parameter Identifiability View
The vast majority of work in self-supervised learning have focused on assessing recovered features by a chosen set of downstream tasks.