Computational notebooks, such as Jupyter notebooks, are interactive comp...
Accurate uncertainty quantification is a major challenge in deep learnin...
State-of-the-art neural models of source code tend to be evaluated on th...
High-quality estimates of uncertainty and robustness are crucial for num...
Ensemble methods which average over multiple neural network predictions ...
Bayesian neural networks (BNNs) demonstrate promising success in improvi...
Ensembles, where multiple neural networks are trained individually and t...
Model-based reinforcement learning (MBRL) is widely seen as having the
p...
The choice of batch-size in a stochastic optimization algorithm plays a
...
Stochastic neural net weights are used in a variety of contexts, includi...