Advanced

Discriminating and Simulating Actions with the Associative Self-Organizing Map

Buonamente, Miriam; Dindo, Haris and Johnsson, Magnus LU (2015) In Connection Science 27(2). p.118-136
Abstract (Swedish)
Abstract in Undetermined

We propose a system able to represent others' actions as well as to internally simulate their likely continuation from a partial observation. The approach presented here is the first step towards a more ambitious goal of endowing an artificial agent with the ability to recognise and predict others' intentions. Our approach is based on the associative self-organising map, a variant of the self-organising map capable of learning to associate its activity with different inputs over time, where inputs are processed observations of others' actions. We have evaluated our system in two different experimental scenarios obtaining promising results: the system demonstrated an ability to learn discriminable... (More)
Abstract in Undetermined

We propose a system able to represent others' actions as well as to internally simulate their likely continuation from a partial observation. The approach presented here is the first step towards a more ambitious goal of endowing an artificial agent with the ability to recognise and predict others' intentions. Our approach is based on the associative self-organising map, a variant of the self-organising map capable of learning to associate its activity with different inputs over time, where inputs are processed observations of others' actions. We have evaluated our system in two different experimental scenarios obtaining promising results: the system demonstrated an ability to learn discriminable representations of actions, to recognise novel input, and to simulate the likely continuation of partially seen actions. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
associative self-organising map, action recognition, internal, simulation, intention understanding, neural network
in
Connection Science
volume
27
issue
2
pages
118 - 136
publisher
Taylor & Francis
external identifiers
  • wos:000354115100003
  • scopus:84929292171
ISSN
0954-0091
DOI
10.1080/09540091.2015.1025571
language
English
LU publication?
yes
id
20693821-2f4e-4f89-8d31-ff11ec3fafa0 (old id 5011242)
date added to LUP
2015-01-29 16:18:22
date last changed
2017-07-09 03:20:41
@article{20693821-2f4e-4f89-8d31-ff11ec3fafa0,
  abstract     = {<b>Abstract in Undetermined</b><br/><br>
We propose a system able to represent others' actions as well as to internally simulate their likely continuation from a partial observation. The approach presented here is the first step towards a more ambitious goal of endowing an artificial agent with the ability to recognise and predict others' intentions. Our approach is based on the associative self-organising map, a variant of the self-organising map capable of learning to associate its activity with different inputs over time, where inputs are processed observations of others' actions. We have evaluated our system in two different experimental scenarios obtaining promising results: the system demonstrated an ability to learn discriminable representations of actions, to recognise novel input, and to simulate the likely continuation of partially seen actions.},
  author       = {Buonamente, Miriam and Dindo, Haris and Johnsson, Magnus},
  issn         = {0954-0091},
  keyword      = {associative self-organising map,action recognition,internal,simulation,intention understanding,neural network},
  language     = {eng},
  number       = {2},
  pages        = {118--136},
  publisher    = {Taylor & Francis},
  series       = {Connection Science},
  title        = {Discriminating and Simulating Actions with the Associative Self-Organizing Map},
  url          = {http://dx.doi.org/10.1080/09540091.2015.1025571},
  volume       = {27},
  year         = {2015},
}