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
Book
Anticipatory Behavior in Adaptive Learning Systems
TL;DR: A cognitive phenomenon is obtained which generates a trace which is denoted as Electroexpectogram (EXG) which shows a learning process represented by the learned anticipation in the CNV anticipatory potential.
Journal ArticleDOI
Hierarchical Active Inference: A Theory of Motivated Control
TL;DR: A novel perspective is offered that casts control and motivational processes as complementary aspects of active inference and hierarchical goal processing under deep generative models and proposes that the control hierarchy propagates prior preferences or goals, but their precision is informed by the motivational context.
Journal ArticleDOI
The mechanics of embodiment: a dialog on embodiment and computational modeling.
Giovanni Pezzulo,Lawrence W. Barsalou,Angelo Cangelosi,Martin H. Fischer,Ken McRae,Michael J. Spivey +5 more
TL;DR: Six authors from varying backgrounds and approaches address issues concerning the construction of embodied computational models, and illustrate what they view as the critical current and next steps toward mechanistic theories of embodiment.
Journal ArticleDOI
Knowing one's place: a free-energy approach to pattern regulation
TL;DR: This work offers a proof of principle that self-assembly is an emergent property of cells that share a common (genetic and epigenetic) model of organismal form and suggests an interpretation of genetic codes as parametrizing a generative model—predicting the signals sensed by cells in the target morphology—and epigenetic processes as the subsequent inversion of that model.
Journal ArticleDOI
The role of domain information in Word Sense Disambiguation
TL;DR: Results obtained at the SENSEVAL-2 initiative confirm that for a significant subset of words domain information can be used to disambiguate with a very high level of precision.