Research Online

Logo

Goldsmiths - University of London

Learning Visual-Motor Cell Assemblies for the iCub Robot using a Neuroanatomically grounded Neural Network

Adams, S.V.; Wennekers, T.; Cangelosi, A.; Pulvermüller, F. and Garagnani, M.. 2014. 'Learning Visual-Motor Cell Assemblies for the iCub Robot using a Neuroanatomically grounded Neural Network'. In: IEEE Symposium Series on Computational Intelligence, Cognitive Algorithms, Mind and Brain (SSCI-CCMB 2014),. Orlando, United States. [Conference or Workshop Item]

[img] Text
Adamsetal_formatted_final.doc - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

Download (25MB)

Abstract or Description

In this work we describe how an existing neural model for learning Cell Assemblies (CAs) across multiple neuroanatomical brain areas has been integrated with a humanoid robot simulation to explore the learning of associations of visual and motor modalities. The results show that robust CAs are learned to enable pattern completion to select a correct motor response when only visual input is presented. We also show, with some parameter tuning and the pre-processing of more realistic patterns taken from images of real objects and robot poses the network can act as a controller for the robot in visuo-motor association tasks. This provides the basis for further neurorobotic experiments on grounded language learning.

Item Type:

Conference or Workshop Item (Paper)

Identification Number (DOI):

https://doi.org/10.1109/CCMB.2014.7020687

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
1 September 2014Published

Event Location:

Orlando, United States

Item ID:

24143

Date Deposited:

19 Sep 2018 09:05

Last Modified:

19 Sep 2018 09:07

URI:

http://research.gold.ac.uk/id/eprint/24143

View statistics for this item...

Edit Record Edit Record (login required)