Discriminating and Simulating Actions with the Associative Self-Organizing Map

Research output: Contribution to journalArticle

Standard

Discriminating and Simulating Actions with the Associative Self-Organizing Map. / Buonamente, Miriam; Dindo, Haris; Johnsson, Magnus.

In: Connection Science, Vol. 27, No. 2, 2015, p. 118-136.

Research output: Contribution to journalArticle

Harvard

APA

CBE

MLA

Vancouver

Author

Buonamente, Miriam ; Dindo, Haris ; Johnsson, Magnus. / Discriminating and Simulating Actions with the Associative Self-Organizing Map. In: Connection Science. 2015 ; Vol. 27, No. 2. pp. 118-136.

RIS

TY - JOUR

T1 - Discriminating and Simulating Actions with the Associative Self-Organizing Map

AU - Buonamente, Miriam

AU - Dindo, Haris

AU - Johnsson, Magnus

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

KW - associative self-organising map

KW - action recognition

KW - internal

KW - simulation

KW - intention understanding

KW - neural network

U2 - 10.1080/09540091.2015.1025571

DO - 10.1080/09540091.2015.1025571

M3 - Article

VL - 27

SP - 118

EP - 136

JO - Connection Science

T2 - Connection Science

JF - Connection Science

SN - 0954-0091

IS - 2

ER -