TY - GEN
T1 - Capturing human category representations by sampling in deep feature spaces
AU - Peterson, Joshua C.
AU - Suchow, Jordan W.
AU - Aghi, Krisha
AU - Ku, Alexander Y.
AU - Griffiths, Thomas L.
N1 - Publisher Copyright:
© 2018 Proceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018. All rights reserved.
PY - 2018
Y1 - 2018
N2 - Understanding how people represent categories is a core problem in cognitive science. Decades of research have yielded a variety of formal theories of categories, but validating them with naturalistic stimuli is difficult. The challenge is that human category representations cannot be directly observed and running informative experiments with naturalistic stimuli such as images requires a workable representation of these stimuli. Deep neural networks have recently been successful in solving a range of computer vision tasks and provide a way to compactly represent image features. 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. We provide qualitative and quantitative results as a proof-of-concept for the method's feasibility. Samples drawn from human distributions rival those from state-of-the-art generative models in quality and outperform alternative methods for estimating the structure of human categories.
AB - Understanding how people represent categories is a core problem in cognitive science. Decades of research have yielded a variety of formal theories of categories, but validating them with naturalistic stimuli is difficult. The challenge is that human category representations cannot be directly observed and running informative experiments with naturalistic stimuli such as images requires a workable representation of these stimuli. Deep neural networks have recently been successful in solving a range of computer vision tasks and provide a way to compactly represent image features. 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. We provide qualitative and quantitative results as a proof-of-concept for the method's feasibility. Samples drawn from human distributions rival those from state-of-the-art generative models in quality and outperform alternative methods for estimating the structure of human categories.
KW - Markov Chain Monte Carlo
KW - categorization
KW - neural networks
UR - http://www.scopus.com/inward/record.url?scp=85112398304&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112398304&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85112398304
T3 - Proceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018
SP - 876
EP - 881
BT - Proceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018
T2 - 40th Annual Meeting of the Cognitive Science Society: Changing Minds, CogSci 2018
Y2 - 25 July 2018 through 28 July 2018
ER -