no code implementations • 23 Apr 2024 • Raphael Koster, Miruna Pîslar, Andrea Tacchetti, Jan Balaguer, Leqi Liu, Romuald Elie, Oliver P. Hauser, Karl Tuyls, Matt Botvinick, Christopher Summerfield
A canonical social dilemma arises when finite resources are allocated to a group of people, who can choose to either reciprocate with interest, or keep the proceeds for themselves.
no code implementations • 29 Jun 2023 • Timo Flesch, Valerio Mante, William Newsome, Andrew Saxe, Christopher Summerfield, David Sussillo
A recent paper (Flesch et al, 2022) describes behavioural and neural data suggesting that task representations are gated in the prefrontal cortex in both humans and macaques.
no code implementations • 22 Feb 2023 • Anika T. Löwe, Léo Touzo, Paul S. Muhle-Karbe, Andrew M. Saxe, Christopher Summerfield, Nicolas W. Schuck
Humans sometimes have an insight that leads to a sudden and drastic performance improvement on the task they are working on.
no code implementations • 28 Nov 2022 • Michiel A. Bakker, Martin J. Chadwick, Hannah R. Sheahan, Michael Henry Tessler, Lucy Campbell-Gillingham, Jan Balaguer, Nat McAleese, Amelia Glaese, John Aslanides, Matthew M. Botvinick, Christopher Summerfield
Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user.
no code implementations • 10 Oct 2022 • Timo Flesch, Andrew Saxe, Christopher Summerfield
How do humans and other animals learn new tasks?
no code implementations • 30 Sep 2022 • Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Tim Genewein, Elliot Catt, Kevin Li, Anian Ruoss, Chris Cundy, Joel Veness, Jane Wang, Marcus Hutter, Christopher Summerfield, Shane Legg, Pedro Ortega
This is in contrast to risk-sensitive agents, which additionally exploit the higher-order moments of the return, and ambiguity-sensitive agents, which act differently when recognizing situations in which they lack knowledge.
1 code implementation • 22 Mar 2022 • Timo Flesch, David G. Nagy, Andrew Saxe, Christopher Summerfield
Here, we propose novel computational constraints for artificial neural networks, inspired by earlier work on gating in the primate prefrontal cortex, that capture the cost of interleaved training and allow the network to learn two tasks in sequence without forgetting.
no code implementations • 21 Feb 2022 • Jan Balaguer, Raphael Koster, Christopher Summerfield, Andrea Tacchetti
Our results show that our mechanisms are able to shepherd the participants strategies towards favorable outcomes, indicating a path for modern institutions to effectively and automatically influence the strategies and behaviors of their constituents.
no code implementations • 21 Feb 2022 • Jan Balaguer, Raphael Koster, Ari Weinstein, Lucy Campbell-Gillingham, Christopher Summerfield, Matthew Botvinick, Andrea Tacchetti
Our analysis shows HCMD-zero consistently makes the mechanism policy more and more likely to be preferred by human participants over the course of training, and that it results in a mechanism with an interpretable and intuitive policy.
no code implementations • 27 Jan 2022 • Raphael Koster, Jan Balaguer, Andrea Tacchetti, Ari Weinstein, Tina Zhu, Oliver Hauser, Duncan Williams, Lucy Campbell-Gillingham, Phoebe Thacker, Matthew Botvinick, Christopher Summerfield
Building artificial intelligence (AI) that aligns with human values is an unsolved problem.
no code implementations • NeurIPS 2020 • Yinan Cao, Christopher Summerfield, Andrew Saxe
Studies suggesting that representations in deep networks resemble those in biological brains have mostly relied on one specific learning rule: gradient descent, the workhorse behind modern deep learning.
no code implementations • 16 Apr 2020 • Andrew Saxe, Stephanie Nelli, Christopher Summerfield
In this Perspective, our goal is to offer a roadmap for systems neuroscience research in the age of deep learning.
Neurons and Cognition