Zobrazeno 1 - 10
of 147
pro vyhledávání: '"PRINCE, SIMON"'
Autor:
Agarwal, Pranav, Rahman, Aamer Abdul, St-Charles, Pierre-Luc, Prince, Simon J. D., Kahou, Samira Ebrahimi
Transformers have significantly impacted domains like natural language processing, computer vision, and robotics, where they improve performance compared to other neural networks. This survey explores how transformers are used in reinforcement learni
Externí odkaz:
http://arxiv.org/abs/2307.05979
Autor:
LaCroix, Travis, Prince, Simon J. D.
This article appears as chapter 21 of Prince (2023, Understanding Deep Learning); a complete draft of the textbook is available here: http://udlbook.com. This chapter considers potential harms arising from the design and use of AI systems. These incl
Externí odkaz:
http://arxiv.org/abs/2305.15239
Machine learning models are vulnerable to biases that result in unfair treatment of individuals from different populations. Recent work that aims to test a model's fairness at the individual level either relies on domain knowledge to choose metrics,
Externí odkaz:
http://arxiv.org/abs/2210.06288
Autor:
Xu, Peng, Kumar, Dhruv, Yang, Wei, Zi, Wenjie, Tang, Keyi, Huang, Chenyang, Cheung, Jackie Chi Kit, Prince, Simon J. D., Cao, Yanshuai
It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work shows tha
Externí odkaz:
http://arxiv.org/abs/2012.15355
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature arou
Externí odkaz:
http://arxiv.org/abs/1908.09257
Autor:
Prince, Simon A.
The focus of this work is the investigation of the complex compressible flow phenomena associated with high speed aerial weapons. A three dimen- sional multiblock finite volume flow solver was developed with the aim of studying the aerodynamics of mi
Externí odkaz:
http://dspace.lib.cranfield.ac.uk/handle/1826/4599