Neural network architecture for crossmodal activation and perceptual sequences

Magnus Johnsson, Christian Balkenius, Germund Hesslow

Forskningsoutput: KonferensbidragArbetsdokument (paper)Peer review

3 Citeringar (Scopus)

Sammanfattning

A self-organizing neural network is described that can associate between different modalities and also has the ability to learn perceptual sequences. This architecture is a step towards the development of a complete agent containing simplified versions of all major neural subsystems in a mammal. It aims at exploring as well as takes inspiration from the idea that cognitive function involves an internal simulation of perception and movement. We have tested the architecture in simulations as well as together with real sensors with very encouraging results.

OriginalspråkEngelska
Sidor85-86
Antal sidor2
StatusPublicerad - 2009
Externt publiceradJa
Evenemang2009 AAAI FAll Symposium - Arlington, VA, USA
Varaktighet: 2009-nov.-052009-nov.-07

Konferens

Konferens2009 AAAI FAll Symposium
Land/TerritoriumUSA
OrtArlington, VA
Period09-11-0509-11-07

Nationell ämneskategori

  • Data- och informationsvetenskap (102)

Fingeravtryck

Fördjupa i forskningsämnen för ”Neural network architecture for crossmodal activation and perceptual sequences”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här