Search Results for author:
Found 3 papers, 2 papers with code
Neurosymbolic Reinforcement Learning and Planning: A Survey
We categorize works based on the role played by the neural and symbolic parts in RL, into three taxonomies:Learning for Reasoning, Reasoning for Learning and Learning-Reasoning.
KamNet: An Integrated Spatiotemporal Deep Neural Network for Rare Event Search in KamLAND-Zen
A key component of this work is the addition of an attention mechanism to elucidate the underlying physics KamNet is using for the background rejection.
No Regret Sample Selection with Noisy Labels
Roughly speaking, a regret, which is defined by the difference between the actual selection and the best selection, of the proposed method is theoretically bounded, even though the best selection is unknown until the end of all epochs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
