Neural Plasticity for Rich and Uncertain Robotic Information Streams

Models of adaptation and neural plasticity are often demonstrated in robotic scenarios with heavily pre-processed and regulated information streams to provide learning algorithms with appropriate, well timed, and meaningful data to match the assumptions of learning rules. On the contrary, natural sc...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Main Authors: Andrea Soltoggio, Frank van der Velde
Formato: Online
Idioma:inglês
Publicado em: Frontiers Media SA 2021
Assuntos:
Acesso em linha:18382
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
_version_ 1869514512374169600
author Andrea Soltoggio
Frank van der Velde
author_browse Andrea Soltoggio
Frank van der Velde
author_facet Andrea Soltoggio
Frank van der Velde
author_sort Andrea Soltoggio
collection Directory of Open Access Books
description Models of adaptation and neural plasticity are often demonstrated in robotic scenarios with heavily pre-processed and regulated information streams to provide learning algorithms with appropriate, well timed, and meaningful data to match the assumptions of learning rules. On the contrary, natural scenarios are often rich of raw, asynchronous, overlapping and uncertain inputs and outputs whose relationships and meaning are progressively acquired, disambiguated, and used for further learning. Therefore, recent research efforts focus on neural embodied systems that rely less on well timed and pre-processed inputs, but rather extract autonomously relationships and features in time and space. In particular, realistic and more complete models of plasticity must account for delayed rewards, noisy and ambiguous data, emerging and novel input features during online learning. Such approaches model the progressive acquisition of knowledge into neural systems through experience in environments that may be affected by ambiguities, uncertain signals, delays, or novel features.
format Online
id doab-20.500.12854ir-54480
institution Directory of Open Access Books
language eng
publishDate 2021
publishDateRange 2021
publishDateSort 2021
publisher Frontiers Media SA
publisherStr Frontiers Media SA
record_format ojs
spelling doab-20.500.12854ir-544802024-04-05T12:35:23Z Neural Plasticity for Rich and Uncertain Robotic Information Streams Andrea Soltoggio Frank van der Velde RC321-571 Q1-390 Neuro-robotics emobodied cognition neural plasticity Neural adaptation Cognitive Modeling thema EDItEUR::P Mathematics and Science::PS Biology, life sciences::PSA Life sciences: general issues::PSAN Neurosciences Models of adaptation and neural plasticity are often demonstrated in robotic scenarios with heavily pre-processed and regulated information streams to provide learning algorithms with appropriate, well timed, and meaningful data to match the assumptions of learning rules. On the contrary, natural scenarios are often rich of raw, asynchronous, overlapping and uncertain inputs and outputs whose relationships and meaning are progressively acquired, disambiguated, and used for further learning. Therefore, recent research efforts focus on neural embodied systems that rely less on well timed and pre-processed inputs, but rather extract autonomously relationships and features in time and space. In particular, realistic and more complete models of plasticity must account for delayed rewards, noisy and ambiguous data, emerging and novel input features during online learning. Such approaches model the progressive acquisition of knowledge into neural systems through experience in environments that may be affected by ambiguities, uncertain signals, delays, or novel features. 2021-02-11T20:48:19Z 2021-02-11T20:48:19Z 2016-01-19 14:05:46 2016 book 18382 16648714 9782889199952 https://directory.doabooks.org/handle/20.500.12854/54480 eng Frontiers Research Topics image/jpeg Attribution 4.0 International http://www.frontiersin.org/books/Neural_Plasticity_for_Rich_and_Uncertain_Robotic_Information_Streams/1043 http://journal.frontiersin.org/researchtopic/3107/neural-plasticity-for-rich-and-uncertain-robotic-information-streams Frontiers Media SA 10.3389/978-2-88919-995-2 10.3389/978-2-88919-995-2 bf5ce210-e72e-4860-ba9b-c305640ff3ae 9782889199952 83 open access
spellingShingle RC321-571
Q1-390
Neuro-robotics
emobodied cognition
neural plasticity
Neural adaptation
Cognitive Modeling
thema EDItEUR::P Mathematics and Science::PS Biology, life sciences::PSA Life sciences: general issues::PSAN Neurosciences
Andrea Soltoggio
Frank van der Velde
Neural Plasticity for Rich and Uncertain Robotic Information Streams
title Neural Plasticity for Rich and Uncertain Robotic Information Streams
title_full Neural Plasticity for Rich and Uncertain Robotic Information Streams
title_fullStr Neural Plasticity for Rich and Uncertain Robotic Information Streams
title_full_unstemmed Neural Plasticity for Rich and Uncertain Robotic Information Streams
title_short Neural Plasticity for Rich and Uncertain Robotic Information Streams
title_sort neural plasticity for rich and uncertain robotic information streams
topic RC321-571
Q1-390
Neuro-robotics
emobodied cognition
neural plasticity
Neural adaptation
Cognitive Modeling
thema EDItEUR::P Mathematics and Science::PS Biology, life sciences::PSA Life sciences: general issues::PSAN Neurosciences
topic_facet RC321-571
Q1-390
Neuro-robotics
emobodied cognition
neural plasticity
Neural adaptation
Cognitive Modeling
thema EDItEUR::P Mathematics and Science::PS Biology, life sciences::PSA Life sciences: general issues::PSAN Neurosciences
url 18382
work_keys_str_mv AT andreasoltoggio neuralplasticityforrichanduncertainroboticinformationstreams
AT frankvandervelde neuralplasticityforrichanduncertainroboticinformationstreams