Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Gouk, Henry"'
We analyze VeLO (versatile learned optimizer), the largest scale attempt to train a general purpose "foundational" optimizer to date. VeLO was trained on thousands of machine learning tasks using over 4000 TPU months with the goal of producing an opt
Externí odkaz:
http://arxiv.org/abs/2310.18191
Numerous benchmarks for Few-Shot Learning have been proposed in the last decade. However all of these benchmarks focus on performance averaged over many tasks, and the question of how to reliably evaluate and tune models trained for individual tasks
Externí odkaz:
http://arxiv.org/abs/2307.02732
Autor:
Bohdal, Ondrej, Tian, Yinbing, Zong, Yongshuo, Chavhan, Ruchika, Li, Da, Gouk, Henry, Guo, Li, Hospedales, Timothy
Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and dense prediction. This naturally raises the question of whether there is
Externí odkaz:
http://arxiv.org/abs/2305.07625
Publikováno v:
ICLR TinyPaper 2023
An indigenous perspective on the effectiveness of debiasing techniques for pre-trained language models (PLMs) is presented in this paper. The current techniques used to measure and debias PLMs are skewed towards the US racial biases and rely on pre-d
Externí odkaz:
http://arxiv.org/abs/2304.11094
Autor:
Chavhan, Ruchika, Gouk, Henry, Stuehmer, Jan, Heggan, Calum, Yaghoobi, Mehrdad, Hospedales, Timothy
Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong inductive biases
Externí odkaz:
http://arxiv.org/abs/2302.12712
This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss landscape that adversaries find difficult to navigate. A common, but not
Externí odkaz:
http://arxiv.org/abs/2208.00862
Providing invariances in a given learning task conveys a key inductive bias that can lead to sample-efficient learning and good generalisation, if correctly specified. However, the ideal invariances for many problems of interest are often not known,
Externí odkaz:
http://arxiv.org/abs/2207.08304
Autor:
Baz, Adrian El, Ullah, Ihsan, Alcobaça, Edesio, Carvalho, André C. P. L. F., Chen, Hong, Ferreira, Fabio, Gouk, Henry, Guan, Chaoyu, Guyon, Isabelle, Hospedales, Timothy, Hu, Shell, Huisman, Mike, Hutter, Frank, Liu, Zhengying, Mohr, Felix, Öztürk, Ekrem, van Rijn, Jan N., Sun, Haozhe, Wang, Xin, Zhu, Wenwu
Publikováno v:
NeurIPS 2021 Competition and Demonstration Track, Dec 2021, On-line, United States
Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are avai
Externí odkaz:
http://arxiv.org/abs/2206.08138
Optimisers are an essential component for training machine learning models, and their design influences learning speed and generalisation. Several studies have attempted to learn more effective gradient-descent optimisers via solving a bi-level optim
Externí odkaz:
http://arxiv.org/abs/2203.02711
We investigate the fundamental performance limitations of learning algorithms in several Domain Generalisation (DG) settings. Motivated by the difficulty with which previously proposed methods have in reliably outperforming Empirical Risk Minimisatio
Externí odkaz:
http://arxiv.org/abs/2202.00563