Articles

AI for Science: The Easy and Hard Problems (Battleday and Gershman; to appear in Philosophical Transactions A: arXiv:2408.14508)

On the informativeness of supervision signals (Sucholutsky*, Battleday*, Collins, Marjieh, Peterson, Singh, Bhatt, Jacoby, Weller, Griffiths; UAI 2023: https://arxiv.org/abs/2211.01407)

From convolutional neural networks to models of higher‐level cognition (and back again) (Battleday*, Peterson*, and Griffiths; Annals of New York Academy of Sciences, The Year in Cognitive Neuroscience, 2021: https://doi.org/10.1111/nyas.14593)

Capturing Human Categorization of Natural Images by Combining Deep Networks and Cognitive models (Battleday*, Peterson*, and Griffiths; Nature Communications 11 Article 5418, 2020: https://www.nature.com/articles/s41467-020-18946-z)

Analogy as Nonparametric Bayesian Inference over Relational Systems (Battleday and Griffiths; In Proceedings for the Annual Meeting of the Cognitive Science Society 2020: https://arxiv.org/abs/2006.04156)

Human Uncertainty Makes Classification More Robust (Peterson*, Battleday*, Griffiths, and Russakovsky; International Conference on Computer Vision 2019: https://arxiv.org/abs/1908.07086)

End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior (Singh, Peterson, Battleday, and Griffiths; In Proceedings of Cognitive Science Society Annual Meeting, 2020: https://arxiv.org/abs/2007.08723)

Modeling human categorization of natural images using deep feature representations (Battleday, Peterson, and Griffiths; arXiv, 2017: https://arxiv.org/abs/1711.04855)

Modafinil for neuroenhancement in healthy non-sleep deprived subjects: a systematic review of cognitive effects (Battleday and Brem; Eur. Neuropsychopharmacol. 171. 2016: https://www.ncbi.nlm.nih.gov/pubmed/26381811)
– The authors respond (Eur Neuropsychopharmacol 26, 2016: 391)
– The authors respond (Eur Neuropsychopharmacol 26, 2016: 394-395)

Modafinil – the ‘smart drug’ leading the charge towards a future of neuroenhancement (Battleday and Brem; The Conversation: https://theconversation.com/modafinil-the-smart-drug-leading-the-charge-towards-a-future-of-neuroenhancement-46477)

Mapping the mechanisms of transcranial alternating current stimulation: a pathway from network effects to cognition (Battleday, Muller, Clayton, and Cohen Kadosh; Frontiers in Psychiatry, 5(162) 2014: https://www.ncbi.nlm.nih.gov/pubmed/25477826)

Presentations

Panel Debate: Machine Learning and Mathematical Discovery (Harvard CSMA: https://www.youtube.com/watch?v=0IF_fCn6-tk)

Introductory Talk: Revolutionary Neuroscience (Mathematics of Neuroscience and AI, Rome, 2024: https://youtu.be/o88mZDBYQTM?si=-OE3vKE6NLma1rrB)

Introductory Talk (AE Spring Summit, San Francisco, 2024: https://youtu.be/-7ZBSVoGATM?si=V2p_sISMYaU1h2y0)

On the Informativeness of Supervision Signals (UAI Spotlight talk 2023)

Going out of book: levels and theories in computational cognitive science (Third International Symposium on the Mathematics of Neuroscience 2022)

Towards an NP-hard model of consciousness (Models of Consciousness 2022)

Relational generalization and analogy (Cognition, Brain, and Behavior seminar series, Harvard 2022)

Psychological Generalization (Fall Seminar Series, Santa Fe Institute 2021)

Life as a Stochastic Process (International Conference of Numerical Analysis and Applied Mathematics 2021)

Analogy, Abstraction, and Relational Generalization (AAAI Fall Symposium Series 2020)

Casting Problems of Relational Generalization as Matrix Imputation (International Conference of Numerical Analysis and Applied Mathematics 2020)

Scaling Up Cognitive Models of Categorization (International Conference of Numerical Analysis and Applied Mathematics 2020)

Analogy as Nonparametric Bayesian Inference over Relational Systems (CogSci 2020)

Human Uncertainty Improves Generalization and Robustness for Natural Image Classification (NeurIPS SVRHM, Vancouver 2019)

Lifelong learning and relational generalization (International Workshop on Biocomputation, Queensland University of Technology, Brisbane 2019)

Modeling Human Categorization of Natural Images using Deep Feature Representations (CogSci 2017)

Posters

CIFAR-10H: A large-scale dataset of human classification uncertainty (Peterson, Battleday, and Griffiths; VSS 2020)

Deep prototype models and human image classification (Singh, Peterson, Battleday, and Griffiths; NeurIPS SVRHM and WIML, Vancouver 2019)

Human uncertainty makes classification more robust( Peterson*, Battleday*, Griffiths, and Russakovsky; ICCV 2019)

Transforming deep feature representations to better capture human categorization behavior (Battleday, Peterson, and Griffiths; CCN 2018)a