Internal Simulation of an Agent`s Intentions

Magnus Johnsson; Miriam Buonamente

doi:10.1007/978-3-642-34274-5_32

Internal Simulation of an Agent`s Intentions

Magnus Johnsson, Miriam Buonamente

Cognitive Science

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

We present the Associative Self-Organizing Map (A-SOM) and propose that it could be used to predict an agent's intentions by internally simulating the behaviour likely to follow initial movements. The A-SOM is a neural network that develops a representation of its input space without supervision, while simultaneously learning to associate its activity with an arbitrary number of additional (possibly delayed) inputs. We argue that the A-SOM would be suitable for the prediction of the likely continuation of the perceived behaviour of an agent by learning to associate activity patterns over time, and thus a way to read its intentions.

Original language	English
Title of host publication	Biologically Inspired Cognitive Architectures 2012 (Advances in Intelligent Systems and Computing)
Editors	Antonio Chella
Publisher	Springer
Pages	175-176
Volume	196
ISBN (Print)	978-3-642-34274-5
DOIs	https://doi.org/10.1007/978-3-642-34274-5_32
Publication status	Published - 2013
Event	Biologically Inspired Cognitive Architectures 2012: Third Annual Meeting of the BICA Society - Palermo, Italy Duration: 2012 Oct 31 → 2012 Nov 3

Publication series

Name
Volume	196
ISSN (Print)	2194-5357

Conference

Conference	Biologically Inspired Cognitive Architectures 2012: Third Annual Meeting of the BICA Society
Country/Territory	Italy
City	Palermo
Period	2012/10/31 → 2012/11/03

Subject classification (UKÄ)

Computer graphics and computer vision

Access to Document

10.1007/978-3-642-34274-5_32

CCL: Thinking in Time: Cognition, Communication and Learning
Sahlén, B. (PI), Gärdenfors, P. (PI), Hesslow, G. (Researcher), Lindgren, M. (PI), Strömqvist, S. (PI), Byström, I. (Administrator), Sjöstrand, E. (Administrator), Mårtensson, J. (Researcher), Andersson, A. (Researcher), Hansson, K. (Researcher), Gullberg, M. (Researcher), Johansson, R. (Researcher), Johansson, M. (Researcher), Falck, A. (Researcher), Roll, M. (Researcher), Ståhlberg, F. (Researcher), Horne, M. (Researcher), Blomberg, F. (Researcher), Johansson, V. (Researcher), Nirme, J. (Research student), Gulz, A. (Researcher), van de Weijer, J. (Researcher), Paradis, C. (Researcher), Tärning, B. (Research student), Bramao, I. (Researcher), Sayehli, S. (Researcher), Löhndorf, S. (Research student), Willners, C. (Researcher), Blomberg, J. (Research assistant), Schötz, S. (Researcher), Haake, M. (Researcher), Brännström, J. (Researcher), Grenner, E. (Research student), Holsanova, J. (Researcher), Wengelin, Å. (Researcher), Johnsson, M. (Researcher), Winberg, S. (Researcher), Balkenius, C. (Researcher), Gharaee, Z. (Researcher) & Bååth, R. (Research student)
Swedish Research Council
2008/01/01 → 2018/12/31
Project: Research

Cite this

@inproceedings{7f9e5a683c8d4a089fc0299b482f36f2,

title = "Internal Simulation of an Agent`s Intentions",

abstract = "We present the Associative Self-Organizing Map (A-SOM) and propose that it could be used to predict an agent's intentions by internally simulating the behaviour likely to follow initial movements. The A-SOM is a neural network that develops a representation of its input space without supervision, while simultaneously learning to associate its activity with an arbitrary number of additional (possibly delayed) inputs. We argue that the A-SOM would be suitable for the prediction of the likely continuation of the perceived behaviour of an agent by learning to associate activity patterns over time, and thus a way to read its intentions.",

author = "Magnus Johnsson and Miriam Buonamente",

year = "2013",

doi = "10.1007/978-3-642-34274-5_32",

language = "English",

isbn = "978-3-642-34274-5",

volume = "196",

publisher = "Springer",

pages = "175--176",

editor = "Antonio Chella",

booktitle = "Biologically Inspired Cognitive Architectures 2012 (Advances in Intelligent Systems and Computing)",

address = "Germany",

note = "Biologically Inspired Cognitive Architectures 2012: Third Annual Meeting of the BICA Society ; Conference date: 31-10-2012 Through 03-11-2012",

}

Johnsson, M & Buonamente, M 2013, Internal Simulation of an Agent`s Intentions. in A Chella (ed.), Biologically Inspired Cognitive Architectures 2012 (Advances in Intelligent Systems and Computing). vol. 196, Springer, pp. 175-176, Biologically Inspired Cognitive Architectures 2012: Third Annual Meeting of the BICA Society, Palermo, Italy, 2012/10/31. https://doi.org/10.1007/978-3-642-34274-5_32

TY - GEN

T1 - Internal Simulation of an Agent`s Intentions

AU - Johnsson, Magnus

AU - Buonamente, Miriam

PY - 2013

Y1 - 2013

N2 - We present the Associative Self-Organizing Map (A-SOM) and propose that it could be used to predict an agent's intentions by internally simulating the behaviour likely to follow initial movements. The A-SOM is a neural network that develops a representation of its input space without supervision, while simultaneously learning to associate its activity with an arbitrary number of additional (possibly delayed) inputs. We argue that the A-SOM would be suitable for the prediction of the likely continuation of the perceived behaviour of an agent by learning to associate activity patterns over time, and thus a way to read its intentions.

AB - We present the Associative Self-Organizing Map (A-SOM) and propose that it could be used to predict an agent's intentions by internally simulating the behaviour likely to follow initial movements. The A-SOM is a neural network that develops a representation of its input space without supervision, while simultaneously learning to associate its activity with an arbitrary number of additional (possibly delayed) inputs. We argue that the A-SOM would be suitable for the prediction of the likely continuation of the perceived behaviour of an agent by learning to associate activity patterns over time, and thus a way to read its intentions.

U2 - 10.1007/978-3-642-34274-5_32

DO - 10.1007/978-3-642-34274-5_32

M3 - Paper in conference proceeding

SN - 978-3-642-34274-5

VL - 196

SP - 175

EP - 176

BT - Biologically Inspired Cognitive Architectures 2012 (Advances in Intelligent Systems and Computing)

A2 - Chella, Antonio

PB - Springer

T2 - Biologically Inspired Cognitive Architectures 2012: Third Annual Meeting of the BICA Society

Y2 - 31 October 2012 through 3 November 2012

ER -

Internal Simulation of an Agent`s Intentions

Abstract

Publication series

Conference

Subject classification (UKÄ)

Access to Document

Fingerprint

Projects

CCL: Thinking in Time: Cognition, Communication and Learning

Cite this