All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

Learning a peripersonal space representation using Conditional Restricted Boltzmann Machine

The result's identifiers

  • Result code in IS VaVaI

    <a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00336244" target="_blank" >RIV/68407700:21230/19:00336244 - isvavai.cz</a>

  • Result on the web

    <a href="http://cogsci.fmph.uniba.sk/kuz2019/files/zbornik/straka-hoffmann.pdf" target="_blank" >http://cogsci.fmph.uniba.sk/kuz2019/files/zbornik/straka-hoffmann.pdf</a>

  • DOI - Digital Object Identifier

Alternative languages

  • Result language

    angličtina

  • Original language name

    Learning a peripersonal space representation using Conditional Restricted Boltzmann Machine

  • Original language description

    We present a neural network learning architecture composed of a Restricted Boltzmann Machine (RBM) and a Conditional RBM (CRBM) that performs multisen- sory integration and prediction, motivated by the problem of learning a representation of defensive peripersonal space. This work follows up on our previous work (Straka and Hoffmann 2017) where we proposed a network composed of a RBM and a feedforward neural network (FFNN). In this work, with a similar 2D simulated scenario, we sought to replace the FFNN with an RBM-like module and opted for the CRBM which is responsible for making a temporal prediction. We demonstrate that the new architecture is capable of learning to map from visual and tactile inputs at a previous time step (without tactile activation) to future activations with the visual stimulus at the “skin” and corresponding tactile activation, including the confidence of the predictions.

  • Czech name

  • Czech description

Classification

  • Type

    D - Article in proceedings

  • CEP classification

  • OECD FORD branch

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

Result continuities

  • Project

    <a href="/en/project/GJ17-15697Y" target="_blank" >GJ17-15697Y: Robot self-calibration and safe physical human-robot interaction inspired by body representations in primate brains</a><br>

  • Continuities

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

Others

  • Publication year

    2019

  • Confidentiality

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

Data specific for result type

  • Article name in the collection

    Kognícia a umelý život 2019

  • ISBN

    978-80-223-4720-4

  • ISSN

  • e-ISSN

  • Number of pages

    2

  • Pages from-to

    104-105

  • Publisher name

    Univerzita Komenského v Bratislave

  • Place of publication

  • Event location

    Hotel Barónka, Bratislava

  • Event date

    May 29, 2019

  • Type of event by nationality

    EUR - Evropská akce

  • UT code for WoS article