Webbläsaren som du använder stöds inte av denna webbplats. Alla versioner av Internet Explorer stöds inte längre, av oss eller Microsoft (läs mer här: * https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Var god och använd en modern webbläsare för att ta del av denna webbplats, som t.ex. nyaste versioner av Edge, Chrome, Firefox eller Safari osv.

Internal Simulation of an Agent`s Intentions

In English

Författare

  • Magnus Johnsson
  • Miriam Buonamente

Redaktör

  • Antonio Chella

Summary, in English

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.

Publiceringsår

2013

Språk

Engelska

Sidor

175-176

Publikation/Tidskrift/Serie

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

Volym

196

Dokumenttyp

Konferensbidrag

Förlag

Springer

Ämne

  • Computer Vision and Robotics (Autonomous Systems)

Conference name

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

Conference date

2012-10-31 - 2012-11-03

Conference place

Palermo, Italy

Status

Published

Projekt

  • Thinking in Time: Cognition, Communication and Learning

ISBN/ISSN/Övrigt

  • ISSN: 2194-5357
  • ISBN: 978-3-642-34274-5