Motor simulation via coupled internal models using sequential Monte Carlo (Contributo in atti di convegno)

Type
Label
  • Motor simulation via coupled internal models using sequential Monte Carlo (Contributo in atti di convegno) (literal)
Anno
  • 2011-01-01T00:00:00+01:00 (literal)
Alternative label
  • Dindo, Haris ; Zambuto, Daniele ; Pezzulo, Giovanni (2011)
    Motor simulation via coupled internal models using sequential Monte Carlo
    in Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, Barcelona, Catalonia, Spain, 16-22 July 2011, Barcelona, 16-22 July 2011
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • Dindo, Haris ; Zambuto, Daniele ; Pezzulo, Giovanni (literal)
Pagina inizio
  • 2113 (literal)
Pagina fine
  • 2119 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#altreInformazioni
  • ID_PUMA: /cnr.istc/2011-A2-012. - Area di valutazione 01 - Scienze matematiche e informatiche ID_PUMA: cnr.ilc/2011-A2-012 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • Consiglio Nazionale delle Ricerche ILC-CNR and ISTC-CNR (literal)
Titolo
  • Motor simulation via coupled internal models using sequential Monte Carlo (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#curatoriVolume
  • T. Walsh (literal)
Abstract
  • We describe a generative Bayesian model for action understanding in which inverse-forward internal model pairs are considered 'hypotheses' of plausible action goals that are explored in parallel via an approximate inference mechanism based on sequential Monte Carlo methods. The reenactment of internal model pairs can be considered a form of motor simulation, which supports both perceptual prediction and action understanding at the goal level. However, this procedure is generally considered to be computationally inefficient. We present a model that dynamically reallocates computational resources to more accurate internal models depending on both the available prior information and the prediction error of the inverse-forward models, and which leads to successful action recognition. We present experimental results that test the robustness and efficiency of our model in real-world scenarios. (literal)
Editore
Prodotto di
Autore CNR
Insieme di parole chiave

Incoming links:


Autore CNR di
Prodotto
Editore di
Insieme di parole chiave di
data.CNR.it