Compositional inductive biases in function learning
| Autor: | Samuel J. Gershman, David Duvenaud, Maarten Speekenbrink, Joshua B. Tenenbaum, Eric Schulz |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Adult
Male Linguistics and Language Computer science Principle of compositionality media_common.quotation_subject Experimental and Cognitive Psychology Machine learning computer.software_genre 050105 experimental psychology Thinking 03 medical and health sciences symbols.namesake 0302 clinical medicine Artificial Intelligence Prior probability Developmental and Educational Psychology Humans Learning 0501 psychology and cognitive sciences Gaussian process media_common Structure (mathematical logic) Grammar Inductive bias business.industry 05 social sciences Numerosity adaptation effect Models Theoretical Neuropsychology and Physiological Psychology Pattern Recognition Visual Pattern recognition (psychology) symbols Female Artificial intelligence Bayesian linear regression business computer 030217 neurology & neurosurgery |
| Zdroj: | bioRxiv Cognitive Neuroscience |
| Popis: | How do people recognize and learn about complex functional structure? Taking inspiration from other areas of cognitive science, we propose that this is achieved by harnessing compositionality: complex structure is decomposed into simpler building blocks. We formalize this idea within the framework of Bayesian regression using a grammar over Gaussian process kernels, and compare this approach with other structure learning approaches. Participants consistently chose compositional (over non-compositional) extrapolations and interpolations of functions. Experiments designed to elicit priors over functional patterns revealed an inductive bias for compositional structure. Compositional functions were perceived as subjectively more predictable than non-compositional functions, and exhibited other signatures of predictability, such as enhanced memorability and reduced numerosity. Taken together, these results support the view that the human intuitive theory of functions is inherently compositional. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|