Neural network architecture for crossmodal activation and perceptual sequences

Magnus Johnsson; Christian Balkenius; Germund Hesslow

Neural network architecture for crossmodal activation and perceptual sequences

Magnus Johnsson, Christian Balkenius, Germund Hesslow

Research output: Contribution to conference › Paper › peer-review

3 Citations (Scopus)

Abstract

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.

Original language	English
Pages	85-86
Number of pages	2
Publication status	Published - 2009
Externally published	Yes
Event	2009 AAAI FAll Symposium - Arlington, VA, United States Duration: 2009-Nov-05 → 2009-Nov-07

Conference

Conference	2009 AAAI FAll Symposium
Country/Territory	United States
City	Arlington, VA
Period	09-11-05 → 09-11-07

Swedish Standard Keywords

Computer and Information Sciences (102)

Cite this

@conference{1b8177b748ab45e5b13c19af4b998a88,

title = "Neural network architecture for crossmodal activation and perceptual sequences",

abstract = "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.",

author = "Magnus Johnsson and Christian Balkenius and Germund Hesslow",

year = "2009",

language = "English",

pages = "85--86",

note = "2009 AAAI FAll Symposium ; Conference date: 05-11-2009 Through 07-11-2009",

}

TY - CONF

T1 - Neural network architecture for crossmodal activation and perceptual sequences

AU - Johnsson, Magnus

AU - Balkenius, Christian

AU - Hesslow, Germund

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

M3 - Paper

AN - SCOPUS:77954224995

SP - 85

EP - 86

T2 - 2009 AAAI FAll Symposium

Y2 - 5 November 2009 through 7 November 2009

ER -

Neural network architecture for crossmodal activation and perceptual sequences

Abstract

Conference

Swedish Standard Keywords

Fingerprint

Cite this