Zobrazeno 1 - 10
of 92
pro vyhledávání: '"Williamson, Sinead A"'
A key question in brain sciences is how to identify time-evolving functional connectivity, such as that obtained from recordings of neuronal activity over time. We wish to explain the observed phenomena in terms of latent states which, in the case of
Externí odkaz:
http://arxiv.org/abs/2411.04229
Autor:
Wu, Luhuan, Williamson, Sinead
In this paper, we approach the problem of uncertainty quantification in deep learning through a predictive framework, which captures uncertainty in model parameters by specifying our assumptions about the predictive distribution of unseen future data
Externí odkaz:
http://arxiv.org/abs/2403.12729
Autor:
Turishcheva, Polina, Ramapuram, Jason, Williamson, Sinead, Busbridge, Dan, Dhekane, Eeshan, Webb, Russ
Publikováno v:
NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice
Understanding model uncertainty is important for many applications. We propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent (BYOL), a negative-free Self-Supervised Learning (SSL) algorithm, with Bayes by Backprop (BBB), a B
Externí odkaz:
http://arxiv.org/abs/2312.03213
In many scientific applications, measured time series are corrupted by noise or distortions. Traditional denoising techniques often fail to recover the signal of interest, particularly when the signal-to-noise ratio is low or when certain assumptions
Externí odkaz:
http://arxiv.org/abs/2211.00080
Graph convolutional networks (GCNs) allow us to learn topologically-aware node embeddings, which can be useful for classification or link prediction. However, they are unable to capture long-range dependencies between nodes without adding additional
Externí odkaz:
http://arxiv.org/abs/2201.12670
Understanding how two datasets differ can help us determine whether one dataset under-represents certain sub-populations, and provides insights into how well models will generalize across datasets. Representative points selected by a maximum mean dis
Externí odkaz:
http://arxiv.org/abs/2006.14621
Autor:
Consul, Shorya, Williamson, Sinead A.
Random forests are a popular method for classification and regression due to their versatility. However, this flexibility can come at the cost of user privacy, since training random forests requires multiple data queries, often on small, identifiable
Externí odkaz:
http://arxiv.org/abs/2006.08795
Machine learning methods allow us to make recommendations to users in applications across fields including entertainment, dating, and commerce, by exploiting similarities in users' interaction patterns. However, in domains that demand protection of p
Externí odkaz:
http://arxiv.org/abs/2003.00602
Publikováno v:
Artificial Intelligence and Statistics, 108:3685-3695, 2020
Bayesian nonparametric (BNP) models provide elegant methods for discovering underlying latent features within a data set, but inference in such models can be slow. We exploit the fact that completely random measures, which commonly used models like t
Externí odkaz:
http://arxiv.org/abs/2001.05591
As the availability and importance of temporal interaction data--such as email communication--increases, it becomes increasingly important to understand the underlying structure that underpins these interactions. Often these interactions form a multi
Externí odkaz:
http://arxiv.org/abs/1910.05098