no code implementations • ICLR 2019 • Ruairidh M. Battleday, Joshua C. Peterson, Thomas L. Griffiths
As deep CNN classifier performance using ground-truth labels has begun to asymptote at near-perfect levels, a key aim for the field is to extend training paradigms to capture further useful structure in natural image data and improve model robustness and generalization.
no code implementations • 14 Jun 2023 • Raja Marjieh, Nori Jacoby, Joshua C. Peterson, Thomas L. Griffiths
Shepard's universal law of generalization is a remarkable hypothesis about how intelligent organisms should perceive similarity.
no code implementations • 2 Nov 2022 • Ilia Sucholutsky, Ruairidh M. Battleday, Katherine M. Collins, Raja Marjieh, Joshua C. Peterson, Pulkit Singh, Umang Bhatt, Nori Jacoby, Adrian Weller, Thomas L. Griffiths
Supervised learning typically focuses on learning transferable representations from training examples annotated by humans.
no code implementations • 17 Jul 2020 • Pulkit Singh, Joshua C. Peterson, Ruairidh M. Battleday, Thomas L. Griffiths
The stimulus representations employed in such models are either hand-designed by the experimenter, inferred circuitously from human judgments, or borrowed from pretrained deep neural networks that are themselves competing models of category learning.
no code implementations • 16 Oct 2019 • Mayank Agrawal, Joshua C. Peterson, Thomas L. Griffiths
In this paper, we offer a way to enable researchers to systematically build models and identify novel phenomena in large datasets.
no code implementations • ICCV 2019 • Joshua C. Peterson, Ruairidh M. Battleday, Thomas L. Griffiths, Olga Russakovsky
We then show that, while contemporary classifiers fail to exhibit human-like uncertainty on their own, explicit training on our dataset closes this gap, supports improved generalization to increasingly out-of-training-distribution test datasets, and confers robustness to adversarial attacks.
no code implementations • 22 May 2019 • David D. Bourgin, Joshua C. Peterson, Daniel Reichman, Thomas L. Griffiths, Stuart J. Russell
To solve this problem, what is needed are machine learning models with appropriate inductive biases for capturing human behavior, and larger datasets.
no code implementations • 26 Apr 2019 • Ruairidh M. Battleday, Joshua C. Peterson, Thomas L. Griffiths
Human categorization is one of the most important and successful targets of cognitive modeling in psychology, yet decades of development and assessment of competing models have been contingent on small sets of simple, artificial experimental stimuli.
no code implementations • 15 Apr 2019 • Ori Plonsky, Reut Apel, Eyal Ert, Moshe Tennenholtz, David Bourgin, Joshua C. Peterson, Daniel Reichman, Thomas L. Griffiths, Stuart J. Russell, Evan C. Carter, James F. Cavanagh, Ido Erev
Here, we introduce BEAST Gradient Boosting (BEAST-GB), a novel hybrid model that synergizes behavioral theories, specifically the model BEAST, with machine learning techniques.
no code implementations • 18 Feb 2019 • Mayank Agrawal, Joshua C. Peterson, Thomas L. Griffiths
Large-scale behavioral datasets enable researchers to use complex machine learning algorithms to better predict human behavior, yet this increased predictive power does not always lead to a better understanding of the behavior in question.
no code implementations • 19 May 2018 • Joshua C. Peterson, Paul Soulos, Aida Nematzadeh, Thomas L. Griffiths
Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations.
no code implementations • 19 May 2018 • Joshua C. Peterson, Jordan W. Suchow, Krisha Aghi, Alexander Y. Ku, Thomas L. Griffiths
Here, we introduce a method to estimate the structure of human categories that combines ideas from cognitive science and machine learning, blending human-based algorithms with state-of-the-art deep image generators.
no code implementations • 19 May 2018 • Jordan W. Suchow, Joshua C. Peterson, Thomas L. Griffiths
Generative models of human identity and appearance have broad applicability to behavioral science and technology, but the exquisite sensitivity of human face perception means that their utility hinges on the alignment of the model's representation to human psychological representations and the photorealism of the generated images.
no code implementations • 13 Nov 2017 • Ruairidh M. Battleday, Joshua C. Peterson, Thomas L. Griffiths
Over the last few decades, psychologists have developed sophisticated formal models of human categorization using simple artificial stimuli.
1 code implementation • 8 Jun 2017 • Joshua C. Peterson, Joshua T. Abbott, Thomas L. Griffiths
These networks learn representations of real-world stimuli that can potentially be leveraged to capture psychological representations.
no code implementations • 12 May 2017 • Dawn Chen, Joshua C. Peterson, Thomas L. Griffiths
Vector-space representations provide geometric tools for reasoning about the similarity of a set of objects and their relationships.
no code implementations • 9 May 2017 • Joshua C. Peterson, Thomas L. Griffiths
Shepard's Universal Law of Generalization offered a compelling case for the first physics-like law in cognitive science that should hold for all intelligent agents in the universe.
no code implementations • 16 Aug 2016 • Steven Tang, Joshua C. Peterson, Zachary A. Pardos
This research lays the ground work for recommendation in a MOOC and other digital learning environments where high volumes of sequential data exist.
5 code implementations • 6 Aug 2016 • Joshua C. Peterson, Joshua T. Abbott, Thomas L. Griffiths
To remedy this, we develop a method for adapting deep features to align with human similarity judgments, resulting in image representations that can potentially be used to extend the scope of psychological experiments.