Alert button
Picture for Jonathan D. Cohen

Jonathan D. Cohen

Alert button

Department of Neuroscience, Princeton University

Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning

Apr 04, 2022
Sreejan Kumar, Ishita Dasgupta, Raja Marjieh, Nathaniel D. Daw, Jonathan D. Cohen, Thomas L. Griffiths

Figure 1 for Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning
Figure 2 for Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning
Figure 3 for Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning
Figure 4 for Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning
Viaarxiv icon

A Self-Supervised Framework for Function Learning and Extrapolation

Jun 14, 2021
Simon N. Segert, Jonathan D. Cohen

Figure 1 for A Self-Supervised Framework for Function Learning and Extrapolation
Figure 2 for A Self-Supervised Framework for Function Learning and Extrapolation
Figure 3 for A Self-Supervised Framework for Function Learning and Extrapolation
Figure 4 for A Self-Supervised Framework for Function Learning and Extrapolation
Viaarxiv icon

Control of mental representations in human planning

May 14, 2021
Mark K. Ho, David Abel, Carlos G. Correa, Michael L. Littman, Jonathan D. Cohen, Thomas L. Griffiths

Figure 1 for Control of mental representations in human planning
Figure 2 for Control of mental representations in human planning
Figure 3 for Control of mental representations in human planning
Viaarxiv icon

Emergent Symbols through Binding in External Memory

Dec 29, 2020
Taylor W. Webb, Ishan Sinha, Jonathan D. Cohen

Figure 1 for Emergent Symbols through Binding in External Memory
Figure 2 for Emergent Symbols through Binding in External Memory
Figure 3 for Emergent Symbols through Binding in External Memory
Figure 4 for Emergent Symbols through Binding in External Memory
Viaarxiv icon

A Memory-Augmented Neural Network Model of Abstract Rule Learning

Dec 15, 2020
Ishan Sinha, Taylor W. Webb, Jonathan D. Cohen

Figure 1 for A Memory-Augmented Neural Network Model of Abstract Rule Learning
Figure 2 for A Memory-Augmented Neural Network Model of Abstract Rule Learning
Figure 3 for A Memory-Augmented Neural Network Model of Abstract Rule Learning
Figure 4 for A Memory-Augmented Neural Network Model of Abstract Rule Learning
Viaarxiv icon

Meta-Learning of Compositional Task Distributions in Humans and Machines

Oct 05, 2020
Sreejan Kumar, Ishita Dasgupta, Jonathan D. Cohen, Nathaniel D. Daw, Thomas L. Griffiths

Figure 1 for Meta-Learning of Compositional Task Distributions in Humans and Machines
Figure 2 for Meta-Learning of Compositional Task Distributions in Humans and Machines
Figure 3 for Meta-Learning of Compositional Task Distributions in Humans and Machines
Figure 4 for Meta-Learning of Compositional Task Distributions in Humans and Machines
Viaarxiv icon

Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks

Jul 20, 2020
Sachin Ravi, Sebastian Musslick, Maia Hamin, Theodore L. Willke, Jonathan D. Cohen

Figure 1 for Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks
Figure 2 for Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks
Figure 3 for Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks
Figure 4 for Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks
Viaarxiv icon

Learning Representations that Support Extrapolation

Jul 09, 2020
Taylor W. Webb, Zachary Dulberg, Steven M. Frankland, Alexander A. Petrov, Randall C. O'Reilly, Jonathan D. Cohen

Figure 1 for Learning Representations that Support Extrapolation
Figure 2 for Learning Representations that Support Extrapolation
Figure 3 for Learning Representations that Support Extrapolation
Figure 4 for Learning Representations that Support Extrapolation
Viaarxiv icon

The Efficiency of Human Cognition Reflects Planned Information Processing

Feb 13, 2020
Mark K. Ho, David Abel, Jonathan D. Cohen, Michael L. Littman, Thomas L. Griffiths

Figure 1 for The Efficiency of Human Cognition Reflects Planned Information Processing
Figure 2 for The Efficiency of Human Cognition Reflects Planned Information Processing
Figure 3 for The Efficiency of Human Cognition Reflects Planned Information Processing
Figure 4 for The Efficiency of Human Cognition Reflects Planned Information Processing
Viaarxiv icon