The result of a conference held at Harvard University, this volume presents some of the exciting interdisciplinary developments that are clarifying how animals and people learn to behave adaptively in a rapidly changing environment. The text focuses on aspects of how recognition learning, reinforcement learning, and motor learning interact to generate adaptive goal-oriented behaviors that can satisfy internal needs -- an important topic for understanding brain function as well as for designing new types of autonomous robots.
Because a dynamic analysis of system interactions is needed to understand these challenging phenomena -- and neural network models provide a natural framework for representing and analyzing such interactions -- all the articles either develop neural network models or provide biological constraints for guiding and testing their design. The result of a conference held at Harvard University, this volume presents some of the exciting interdisciplinary developments that clarify how animals and people learn to behave adaptively in a rapidly changing environment. The contributors focus on aspects of how recognition learning, reinforcement learning, and motor learning interact to generate adaptive goal-oriented behaviors that can satisfy internal needs -- an area of inquiry as important for understanding brain function as it is for designing new types of autonomous robots.
Because a dynamic analysis of system interactions is needed to understand these challenging phenomena -- and neural network models provide a natural framework for representing and analyzing such interactions -- all the articles either develop neural network models or provide biological constraints for guiding and testing their design.
Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.
The result of a conference held at Harvard University, this volume presents some of the exciting interdisciplinary developments that are clarifying how animals and people learn to behave adaptively in a rapidly changing environment. The text focuses on aspects of how recognition learning, reinforcement learning, and motor learning interact to generate adaptive goal-oriented behaviors that can satisfy internal needs -- an important topic for understanding brain function as well as for designing new types of autonomous robots.
Because a dynamic analysis of system interactions is needed to understand these challenging phenomena -- and neural network models provide a natural framework for representing and analyzing such interactions -- all the articles either develop neural network models or provide biological constraints for guiding and testing their design. The result of a conference held at Harvard University, this volume presents some of the exciting interdisciplinary developments that clarify how animals and people learn to behave adaptively in a rapidly changing environment. The contributors focus on aspects of how recognition learning, reinforcement learning, and motor learning interact to generate adaptive goal-oriented behaviors that can satisfy internal needs -- an area of inquiry as important for understanding brain function as it is for designing new types of autonomous robots.
Because a dynamic analysis of system interactions is needed to understand these challenging phenomena -- and neural network models provide a natural framework for representing and analyzing such interactions -- all the articles either develop neural network models or provide biological constraints for guiding and testing their design.
Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.
Vendeur : Better World Books, Mishawaka, IN, Etats-Unis
Etat : Good. Former library copy. Pages intact with minimal writing/highlighting. The binding may be loose and creased. Dust jackets/supplements are not included. Includes library markings. Stock photo provided. Product includes identifying sticker. Better World Books: Buy Books. Do Good. N° de réf. du vendeur GRP101765402
Quantité disponible : 1 disponible(s)