Learning a Peripersonal Space Representation as a Visuo-Tactile Prediction Task

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00315236" target="_blank" >RIV/68407700:21230/17:00315236 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-68600-4_13" target="_blank" >http://dx.doi.org/10.1007/978-3-319-68600-4_13</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-68600-4_13" target="_blank" >10.1007/978-3-319-68600-4_13</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Learning a Peripersonal Space Representation as a Visuo-Tactile Prediction Task

Popis výsledku v původním jazyce

The space immediately surrounding our body, or peripersonal space, is crucial for interaction with the environment. In primate brains, specific neural circuitry is responsible for its encoding. An important component is a safety margin around the body that draws on visuo-tactile interactions: approaching stimuli are registered by vision and processed, producing anticipation or prediction of contact in the tactile modality. The mechanisms of this representation and its development are not understood. We propose a computational model that addresses this: a neural network composed of a Restricted Boltzmann Machine and a feedforward neural network. The former learns in an unsupervised manner to represent position and velocity features of the stimulus. The latter is trained in a supervised way to predict the position of touch (contact). Unique to this model, it considers: (i) stimulus position and velocity, (ii) uncertainty of all variables, and (iii) not only multisensory integration but also prediction.

Název v anglickém jazyce

Learning a Peripersonal Space Representation as a Visuo-Tactile Prediction Task

Popis výsledku anglicky

The space immediately surrounding our body, or peripersonal space, is crucial for interaction with the environment. In primate brains, specific neural circuitry is responsible for its encoding. An important component is a safety margin around the body that draws on visuo-tactile interactions: approaching stimuli are registered by vision and processed, producing anticipation or prediction of contact in the tactile modality. The mechanisms of this representation and its development are not understood. We propose a computational model that addresses this: a neural network composed of a Restricted Boltzmann Machine and a feedforward neural network. The former learns in an unsupervised manner to represent position and velocity features of the stimulus. The latter is trained in a supervised way to predict the position of touch (contact). Unique to this model, it considers: (i) stimulus position and velocity, (ii) uncertainty of all variables, and (iii) not only multisensory integration but also prediction.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GJ17-15697Y" target="_blank" >GJ17-15697Y: Automatická kalibrace robotů a bezpečná fyzická interakce s člověkem inspirovaná reprezentacemi těla v mozku primátů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Artificial Neural Networks and Machine Learning – ICANN 2017, Part I

ISBN

978-3-319-68599-1

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

9

Strana od-do

101-109

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Alghero

Datum konání akce

11. 9. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—