Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Internal Simulation of an Agent`s Intentions

Johnsson, Magnus LU and Buonamente, Miriam LU (2013) Biologically Inspired Cognitive Architectures 2012: Third Annual Meeting of the BICA Society 196. p.175-176
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.
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Biologically Inspired Cognitive Architectures 2012 (Advances in Intelligent Systems and Computing)
editor
Chella, Antonio
volume
196
pages
175 - 176
publisher
Springer
conference name
Biologically Inspired Cognitive Architectures 2012: Third Annual Meeting of the BICA Society
conference location
Palermo, Italy
conference dates
2012-10-31 - 2012-11-03
external identifiers
  • wos:000313923100032
  • scopus:84870772018
ISSN
2194-5357
ISBN
978-3-642-34274-5
DOI
10.1007/978-3-642-34274-5_32
project
Thinking in Time: Cognition, Communication and Learning
language
English
LU publication?
yes
id
7f9e5a68-3c8d-4a08-9fc0-299b482f36f2 (old id 3437751)
date added to LUP
2016-04-01 15:00:28
date last changed
2022-01-28 03:37:34
@inproceedings{7f9e5a68-3c8d-4a08-9fc0-299b482f36f2,
  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       = {{Johnsson, Magnus and Buonamente, Miriam}},
  booktitle    = {{Biologically Inspired Cognitive Architectures 2012 (Advances in Intelligent Systems and Computing)}},
  editor       = {{Chella, Antonio}},
  isbn         = {{978-3-642-34274-5}},
  issn         = {{2194-5357}},
  language     = {{eng}},
  pages        = {{175--176}},
  publisher    = {{Springer}},
  title        = {{Internal Simulation of an Agent`s Intentions}},
  url          = {{http://dx.doi.org/10.1007/978-3-642-34274-5_32}},
  doi          = {{10.1007/978-3-642-34274-5_32}},
  volume       = {{196}},
  year         = {{2013}},
}