no code implementations • 13 Dec 2022 • Samuel J. Bell, Levent Sagun
Finally, we present two real-world examples of difficulty amplification in action, resulting in worse-than-expected performance disparities between groups even when using a balanced dataset.
no code implementations • 13 Jun 2022 • Samuel J. Bell, Onno P. Kampman, Jesse Dodge, Neil D. Lawrence
Amid mounting concern about the reliability and credibility of machine learning research, we present a principled framework for making robust and generalizable claims: the multiverse analysis.
no code implementations • 26 May 2022 • Samuel J. Bell, Neil D. Lawrence
Connecting to the field of curriculum learning, we show that the effect of task ordering can be exploited to modify continual learning performance, and present a simple approach for doing so.
no code implementations • 20 Oct 2021 • Samuel J. Bell, Neil D. Lawrence
In this paper we explore whether the fundamental tool of experimental psychology, the behavioral experiment, has the power to generate insight not only into humans and animals, but artificial systems too.
no code implementations • 18 Apr 2021 • Samuel J. Bell, Onno P. Kampman
In the early 2010s, a crisis of reproducibility rocked the field of psychology.