Zobrazeno 1 - 10
of 1 411
pro vyhledávání: '"JONES, MATT"'
Autor:
He, Zihong, Lin, Weizhe, Zheng, Hao, Zhang, Fan, Jones, Matt, Aitchison, Laurence, Xu, Xuhai, Liu, Miao, Kristensson, Per Ola, Shen, Junxiao
With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the perfor
Externí odkaz:
http://arxiv.org/abs/2411.00489
The evolution of biological neural systems has led to both modularity and sparse coding, which enables efficiency in energy usage, and robustness across the diversity of tasks in the lifespan. In contrast, standard neural networks rely on dense, non-
Externí odkaz:
http://arxiv.org/abs/2410.08003
Autor:
Jones, Matt
There has been recent interest in whether the concept of quantum contextuality can be extended to systems with disturbance or signaling while retaining the essential properties of standard contextuality. Dzhafarov and Kujala (arXiv:2302.11995) offer
Externí odkaz:
http://arxiv.org/abs/2410.05723
Publikováno v:
NeurIPS 2024
We propose a novel approach to sequential Bayesian inference based on variational Bayes (VB). The key insight is that, in the online setting, we do not need to add the KL term to regularize to the prior (which comes from the posterior at the previous
Externí odkaz:
http://arxiv.org/abs/2405.19681
Autor:
Duran-Martin, Gerardo, Altamirano, Matias, Shestopaloff, Alexander Y., Sánchez-Betancourt, Leandro, Knoblauch, Jeremias, Jones, Matt, Briol, François-Xavier, Murphy, Kevin
We derive a novel, provably robust, and closed-form Bayesian update rule for online filtering in state-space models in the presence of outliers and misspecified measurement models. Our method combines generalised Bayesian inference with filtering met
Externí odkaz:
http://arxiv.org/abs/2405.05646
We explore the training dynamics of neural networks in a structured non-IID setting where documents are presented cyclically in a fixed, repeated sequence. Typically, networks suffer from catastrophic interference when training on a sequence of docum
Externí odkaz:
http://arxiv.org/abs/2403.09613
It is well known that the class of rotation invariant algorithms are suboptimal even for learning sparse linear problems when the number of examples is below the "dimension" of the problem. This class includes any gradient descent trained neural net
Externí odkaz:
http://arxiv.org/abs/2403.02697
Simultaneous localisation and mapping (SLAM) algorithms are commonly used in robotic systems for learning maps of novel environments. Brains also appear to learn maps, but the mechanisms are not known and it is unclear how to infer these maps from ne
Externí odkaz:
http://arxiv.org/abs/2402.00588
Autor:
Chang, Peter G., Durán-Martín, Gerardo, Shestopaloff, Alexander Y, Jones, Matt, Murphy, Kevin
Publikováno v:
COLLAS conference 2023
We propose an efficient online approximate Bayesian inference algorithm for estimating the parameters of a nonlinear function from a potentially non-stationary data stream. The method is based on the extended Kalman filter (EKF), but uses a novel low
Externí odkaz:
http://arxiv.org/abs/2305.19535