Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Buonamente"'
Publikováno v:
In Biologically Inspired Cognitive Architectures August 2018 25:135-140
Publikováno v:
In Cognitive Systems Research September 2016 39:33-41
Publikováno v:
Biologically Inspired Cognitive Architectures. 25:135-140
We present an architecture able to recognise pitches and to internally simulate likely continuations of partially heard melodies. Our architecture consists of a novel version of the Associative Self-Organizing Map (A-SOM) with generalized ancillary c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9d48b283ad0aab2108cd17dd4b3f299
https://doi.org/10.1016/j.bica.2018.07.006
https://doi.org/10.1016/j.bica.2018.07.006
Publikováno v:
Cognitive Systems Research. 39:33-41
We propose a hierarchical neural architecture able to recognise observed human actions. Each layer in the architecture represents increasingly complex human activity features. The first layer consists of a SOM which performs dimensionality reduction
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c367677cddd5f1de8a90efb1d2edfe1a
https://doi.org/10.1016/j.cogsys.2015.12.009
https://doi.org/10.1016/j.cogsys.2015.12.009
Publikováno v:
Connection Science. 27:118-136
We propose a system able to represent others’ actions as well as to internally simulate their likely continuation from a partial observation. The approach presented here is the first step towards a more ambitious goal of endowing an artificial agen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f30195ceeac942563f6ba6e2ccfd3e97
https://doi.org/10.1080/09540091.2015.1025571
https://doi.org/10.1080/09540091.2015.1025571
Autor:
Buonamente, Miriam1 (AUTHOR) miriam.buonamente@unipa.it, Dindo, Haris1 (AUTHOR), Johnsson, Magnus2 (AUTHOR)
Publikováno v:
Connection Science. Jun2015, Vol. 27 Issue 2, p118-136. 19p.
We propose a hierarchical neural architecture able to recognise observed human actions. Each layer in the architecture represents increasingly complex human activity features. The first layer consists of a SOM which performs dimensionality reduction
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3658::759c312716b92ded035a8e0244bc6130
http://hdl.handle.net/10447/103819
http://hdl.handle.net/10447/103819
Publikováno v:
ICAT
When artificial agents interact and cooperate with other agents, either human or artificial, they need to recognize others’ actions and infer their hidden intentions from the sole observation of their surface level movements. Indeed, action and int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::679e8bf51685457b5afd2a02038ad11b
https://doi.org/10.1109/icat.2013.6684076
https://doi.org/10.1109/icat.2013.6684076
Autor:
Magnus Johnsson, Miriam Buonamente
Publikováno v:
Biologically Inspired Cognitive Architectures 2012 ISBN: 9783642342738
BICA
BICA
We propose an architecture (discussed in the context of a dressing and cleaning application for impaired and elderly persons) that combines a cognitive framework that generates motor commands with the MOSAIC architecture which selects the right motor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::822176c282d2dafad66453e4609423db
https://doi.org/10.1007/978-3-642-34274-5_62
https://doi.org/10.1007/978-3-642-34274-5_62
We present a system that can learn to represent actions as well as to internally simulate the likely continuation of their initial parts. The method we propose is based on the Associative Self Organizing Map (A-SOM), a variant of the Self Organizing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3658::e3efed299a5e5c7a82b2f1f78adac4d9
http://hdl.handle.net/10447/95606
http://hdl.handle.net/10447/95606