1 code implementation • NeurIPS 2021 • Pavel Izmailov, Patrick Nicholson, Sanae Lotfi, Andrew Gordon Wilson
Approximate Bayesian inference for neural networks is considered a robust alternative to standard training, often providing good performance on out-of-distribution data.
no code implementations • Information Retrieval Journal 2019 • Guruprasad Nayak, Sourav Dutta, Deepak Ajwani, Patrick Nicholson, Alessandra Sala
In this paper, we focus on measures that leverage structural properties of the knowledge hierarchy graph to assess the temporal changes.