G
Giovanni Pezzulo
Researcher at National Research Council
Publications - 252
Citations - 10810
Giovanni Pezzulo is an academic researcher from National Research Council. The author has contributed to research in topics: Cognition & Inference. The author has an hindex of 46, co-authored 224 publications receiving 8401 citations. Previous affiliations of Giovanni Pezzulo include Rice University & Google.
Papers
More filters
Efficient coding of facial stimuli in primate inferotemporal cortex
TL;DR: It is shown that despite decoupled coding encodes two sets of (shape and texture) coordinates, it is more efficient (i.e., yields more information compression) than the widely used eigenface method, which only requires encoding the original facial images.
Information-theoretical analysis of the neural code for decoupled face representation
TL;DR: In this paper , a decoupled encoding of facial images in terms of two sets of principal components (of landmark shape and image texture) is proposed, which is more efficient than the eigenface method.
Neurons in the Rat Striatum Inhibitory Interactions Between Spiny Projection
Dorothy E. Oorschot,Annabel Kean,Jeffery R. Wickens,Sriraman Damodaran,Rebekah C. Evans,Kim T. Blackwell,Paul F. M. J. Verschure,Cyriel M. A. Pennartz,Giovanni Pezzulo,John R. Cressman,Zbigniew Jedrzejewski-Szmek +10 more
Proceedings ArticleDOI
Integrating a MAS and a Pandemonium: the open-source framework AKIRA
TL;DR: The main components of the framework AKIRA are described, showing that the hybrid nature of the Agents, having symbolic and connectionist features, permits to model many functionalities such as implicit communication and coordination.
Journal ArticleDOI
Skilled motor control of an inverted pendulum implies low entropy of states but high entropy of actions
Nicola Catenacci Volpi,Martin Greaves,Dari Trendafilov,Christoph Salge,Giovanni Pezzulo,Daniel Polani +5 more
TL;DR: In this paper , the authors studied how participants managed control tasks of varying levels of difficulty, which consisted of balancing an inverted pendulum of different lengths, and found that the successful performance of the control task strongly correlates with the decrease of state variability and the increase of action variability.