Alert button
Picture for Christopher Summerfield

Christopher Summerfield

Alert button

Regularised neural networks mimic human insight

Feb 22, 2023
Anika T. Löwe, Léo Touzo, Paul S. Muhle-Karbe, Andrew M. Saxe, Christopher Summerfield, Nicolas W. Schuck

Figure 1 for Regularised neural networks mimic human insight
Figure 2 for Regularised neural networks mimic human insight
Figure 3 for Regularised neural networks mimic human insight
Figure 4 for Regularised neural networks mimic human insight
Viaarxiv icon

Fine-tuning language models to find agreement among humans with diverse preferences

Nov 28, 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

Figure 1 for Fine-tuning language models to find agreement among humans with diverse preferences
Figure 2 for Fine-tuning language models to find agreement among humans with diverse preferences
Figure 3 for Fine-tuning language models to find agreement among humans with diverse preferences
Figure 4 for Fine-tuning language models to find agreement among humans with diverse preferences
Viaarxiv icon

Beyond Bayes-optimality: meta-learning what you know you don't know

Oct 12, 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

Figure 1 for Beyond Bayes-optimality: meta-learning what you know you don't know
Figure 2 for Beyond Bayes-optimality: meta-learning what you know you don't know
Figure 3 for Beyond Bayes-optimality: meta-learning what you know you don't know
Figure 4 for Beyond Bayes-optimality: meta-learning what you know you don't know
Viaarxiv icon

Continual task learning in natural and artificial agents

Oct 10, 2022
Timo Flesch, Andrew Saxe, Christopher Summerfield

Figure 1 for Continual task learning in natural and artificial agents
Figure 2 for Continual task learning in natural and artificial agents
Figure 3 for Continual task learning in natural and artificial agents
Viaarxiv icon

Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals

Mar 22, 2022
Timo Flesch, David G. Nagy, Andrew Saxe, Christopher Summerfield

Figure 1 for Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals
Figure 2 for Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals
Figure 3 for Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals
Figure 4 for Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals
Viaarxiv icon

The Good Shepherd: An Oracle Agent for Mechanism Design

Feb 21, 2022
Jan Balaguer, Raphael Koster, Christopher Summerfield, Andrea Tacchetti

Figure 1 for The Good Shepherd: An Oracle Agent for Mechanism Design
Figure 2 for The Good Shepherd: An Oracle Agent for Mechanism Design
Figure 3 for The Good Shepherd: An Oracle Agent for Mechanism Design
Viaarxiv icon

HCMD-zero: Learning Value Aligned Mechanisms from Data

Feb 21, 2022
Jan Balaguer, Raphael Koster, Ari Weinstein, Lucy Campbell-Gillingham, Christopher Summerfield, Matthew Botvinick, Andrea Tacchetti

Figure 1 for HCMD-zero: Learning Value Aligned Mechanisms from Data
Figure 2 for HCMD-zero: Learning Value Aligned Mechanisms from Data
Figure 3 for HCMD-zero: Learning Value Aligned Mechanisms from Data
Figure 4 for HCMD-zero: Learning Value Aligned Mechanisms from Data
Viaarxiv icon

Human-centered mechanism design with Democratic AI

Jan 27, 2022
Raphael Koster, Jan Balaguer, Andrea Tacchetti, Ari Weinstein, Tina Zhu, Oliver Hauser, Duncan Williams, Lucy Campbell-Gillingham, Phoebe Thacker, Matthew Botvinick, Christopher Summerfield

Figure 1 for Human-centered mechanism design with Democratic AI
Figure 2 for Human-centered mechanism design with Democratic AI
Figure 3 for Human-centered mechanism design with Democratic AI
Figure 4 for Human-centered mechanism design with Democratic AI
Viaarxiv icon