no code implementations • 24 May 2023 • Travis LaCroix, Simon J. D. Prince
This article appears as chapter 21 of Prince (2023, Understanding Deep Learning); a complete draft of the textbook is available here: http://udlbook. com.
no code implementations • 2 Jul 2022 • Travis LaCroix
I discuss the consequences that the truth of this claim would have for research programmes that attempt to ensure value alignment for AI systems; or, more loftily, designing robustly beneficial or ethical artificial agents.
no code implementations • 11 Apr 2022 • Travis LaCroix, Alexandra Sasha Luccioni
In this paper, drawing upon research in moral philosophy and metaethics, we argue that it is impossible to develop such a benchmark.
no code implementations • 11 Mar 2022 • Travis LaCroix
Autonomous systems are being developed and deployed in situations that may require some degree of ethical decision-making ability.
no code implementations • 15 Dec 2021 • Arianna Falbo, Travis LaCroix
Cultural code-switching concerns how we adjust our overall behaviours, manners of speaking, and appearance in response to a perceived change in our social environment.
1 code implementation • 25 Jan 2021 • Michael Noukhovitch, Travis LaCroix, Angeliki Lazaridou, Aaron Courville
First, we show that communication is proportional to cooperation, and it can occur for partially competitive scenarios using standard learning algorithms.
no code implementations • 9 Jun 2020 • Travis LaCroix, Aydin Mohseni
These are supposed to guide the socially-responsible development of AI for the common good.
no code implementations • 29 Dec 2019 • Travis LaCroix, Yoshua Bengio
There is an analogy between machine learning systems and economic entities in that they are both adaptive, and their behaviour is specified in a more-or-less explicit way.
no code implementations • 26 Nov 2019 • Travis LaCroix
This has theoretical implications for language origins research more generally, but the focus here will be the implications for research on emergent communication in computer science and machine learning---specifically regarding the types of programmes that might be expected to work and those which will not.
no code implementations • 25 Sep 2019 • Michael Noukhovitch, Travis LaCroix, Aaron Courville
Current literature in machine learning holds that unaligned, self-interested agents do not learn to use an emergent communication channel.