Predictive Representations: Building Blocks of Intelligence
Neural Computation · 11.10.2024 · 36 (11) · 2225-2298
DOI: 10.1162/neco_a_01705 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Neural Computation, online erschienen am 11.10.2024. Verfasst von Wilka Carvalho und 4 weiteren Autor:innen. Beteiligte Einrichtung: Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Cambridge, MA 02134, U.S.A. wcarvalho92@gmail.com. Hauptthemen laut MEDLINE: Intelligence. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 221 Literaturangaben. Gefördert von: Wellcome Trust, Kempner Institute for the Study of Natural and Artificial Intelligence.
Abstract (Originalsprache)
Adaptive behavior often requires predicting future events. The theory of reinforcement learning prescribes what kinds of predictive representations are useful and how to compute them. This review integrates these theoretical ideas with work on cognition and neuroscience. We pay special attention to the successor representation and its generalizations, which have been widely applied as both engineering tools and models of brain function. This convergence suggests that particular kinds of predictive representations may function as versatile building blocks of intelligence.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Cambridge, MA 02134, U.S.A. wcarvalho92@gmail.com.
- Department of Psychology and Center for Brain Science, Harvard University, Cambridge, MA 02134, U.S.A.
- Motional AD LLC, Boston, MA 02210, U.S.A. tomov90@gmail.com.
- Department of Cell and Developmental Biology, University College London, London WC1E 7JE, U.K. w.decothi@ucl.ac.uk.
- Department of Cell and Developmental Biology, University College London, London WC1E 7JE, U.K. caswell.barry@ucl.ac.uk.
- Kempner Institute for the Study of Natural and Artificial Intelligence, and Department of Psychology and Center for Brain Science, Harvard University, Cambridge, MA 02134, U.S.A.
Förderung
- Wellcome Trust
- Kempner Institute for the Study of Natural and Artificial Intelligence
Zitieren
APA
Carvalho, W., Tomov, M. S., de Cothi, W., Barry, C., & Gershman, S. J. (2024). Predictive Representations: Building Blocks of Intelligence. Neural Computation, 36(11), 2225-2298. https://doi.org/10.1162/neco_a_01705
Vancouver
Carvalho W, Tomov MS, de Cothi W, Barry C, Gershman SJ. Predictive Representations: Building Blocks of Intelligence. Neural Computation. 2024;36(11):2225-2298. doi:10.1162/neco_a_01705
BibTeX
@article{Carvalho2024,
author = {Carvalho, Wilka and Tomov, Momchil S and de Cothi, William and Barry, Caswell and Gershman, Samuel J},
title = {Predictive Representations: Building Blocks of Intelligence},
journal = {Neural Computation},
year = {2024},
volume = {36},
number = {11},
pages = {2225--2298},
doi = {10.1162/neco_a_01705}
}
EUVIMED