About Me

I'm an Assistant Professor in the Faculty of Computing and Data Sciences at Boston University. Before starting at BU, I completed my PhD at UC Berkeley as a member of the Berkeley Artificial Intelligence Research Lab studying the intersection of machine learning and cognitive science. I continued this work as a postdoc at Princeton University in the Department of Computer Science. My recent work explores how machine learning can be used to automate the search for interpretable, high-precision models of human behavior.

Featured Work

Capturing the complexity of human strategic decision-making with machine learning

Zhu Jian-Qiao, Joshua Peterson, Benjamin Enke, Thomas Griffiths (2025)


Nature Human Behavior

PDF

A foundation model to predict and capture human cognition

Marcel Binz, ..., Joshua Peterson, [full author list] (2025)


Nature

PDF

Predicting Human Decisions with Behavioral Theories and Machine Learning

Ori Plonsky, ..., Joshua Peterson, [full author list] (2025)


Nature Human Behavior

PDF

Large language models assume people are more rational than we really are

Ryan Liu, Jiayi Geng, Joshua Peterson, Ilia Sucholutsky, and Thomas Griffiths (2025)

ICLR

PDF

On the informativeness of supervision signals

Ilia Sucholutsky, Ruairidh Battleday, Katherine Collins, Raja Marjieh, Joshua Peterson, Pulkit Singh, Umang Bhatt, Nori Jacoby, Adrian Weller, and Thomas Griffiths (2023)

UAI

PDF

Deep models of superficial face judgments

Joshua Peterson, Stefan Uddenberg, Thomas Griffiths, Alexander Todorov, Jordan Suchow (2022)

PNAS

PDF DATASET

Using large-scale experiments and machine learning to discover theories of human decision-making

Joshua Peterson, David Bourgin, Mayank Agrawal, Daniel Reichman, Thomas Griffiths (2021)

Science

PDF DATASET

Capturing human categorization of natural images by combining deep networks and cognitive models

Ruairidh Battleday*, Joshua Peterson*, Thomas Griffiths (2020)

Nature Communications

PDF DATASET

* equal contribution

Scaling up psychology via Scientific Regret Minimization

Mayank Agrawal, Joshua Peterson, Thomas Griffiths (2020)

PNAS

PDF DATASET

Human uncertainty makes classification more robust

Joshua Peterson*, Ruairidh Battleday*, Thomas Griffiths, Olga Russakovsky (2019)

ICCV

PDF DATASET

* equal contribution

Cognitive model priors for predicting human decisions

David Bourgin*, Joshua Peterson*, Daniel Reichman, Thomas Griffiths, Stuart Russell (2019)

ICML

PDF DATASET

* equal contribution

Other Work

Machine learning for modeling human decisions

Daniel Reichman, Joshua Peterson, and Thomas Griffiths (2024)

Decision

PDF

The Universal Law of Generalization holds for naturalistic stimuli (APA's Editor's Choice)

Raja Marjieh, Nori Jacoby, Joshua Peterson, and Thomas Griffiths (2024)

JEP: General

PDF

Stress, intertemporal choice, and mitigation behavior during the COVID-19 pandemic

Mayank Agrawal, Joshua Peterson, Jonathan D. Cohen, and Thomas Griffiths (2023)

JEP: General

PDF

From convolutional neural networks to models of higher-level cognition (and back again)

Ruairidh Battleday*, Joshua Peterson*, Thomas Griffiths (2021)

Annals of the New York Academy of Sciences

BibTeX PDF

* equal contribution