Self-Organizing Neural Population Coding for improving robotic visuomotor coordination

Tao Zhou; Piotr Dudek; Bertram E. Shi

doi:10.1109/IJCNN.2011.6033393

Self-Organizing Neural Population Coding for improving robotic visuomotor coordination

Tao Zhou, Piotr Dudek, Bertram E. Shi

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

We present an extension of Kohonen's Self Organizing Map (SOM) algorithm called the Self Organizing Neural Population Coding (SONPC) algorithm. The algorithm adapts online the neural population encoding of sensory and motor coordinates of a robot according to the underlying data distribution. By allocating more neurons towards area of sensory or motor space which are more frequently visited, this representation improves the accuracy of a robot system on a visually guided reaching task. We also suggest a Mean Reflection method to solve the notorious border effect problem encountered with SOMs for the special case where the latent space and the data space dimensions are the same. © 2011 IEEE.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks\|Proc Int Jt Conf Neural Networks
Pages	1437-1444
Number of pages	7
DOIs	https://doi.org/10.1109/IJCNN.2011.6033393
Publication status	Published - 2011
Event	2011 International Joint Conference on Neural Network, IJCNN 2011 - San Jose, CA Duration: 1 Jul 2011 → … http://dx.doi.org/10.1109/IJCNN.2011.6033393

Conference

Conference	2011 International Joint Conference on Neural Network, IJCNN 2011
City	San Jose, CA
Period	1/07/11 → …
Internet address	http://dx.doi.org/10.1109/IJCNN.2011.6033393

Keywords

robot vision
self-organising feature maps

Access to Document

10.1109/IJCNN.2011.6033393

Cite this

@inproceedings{05a564fd5b9646fbbfc4452d0247a53c,

title = "Self-Organizing Neural Population Coding for improving robotic visuomotor coordination",

abstract = "We present an extension of Kohonen's Self Organizing Map (SOM) algorithm called the Self Organizing Neural Population Coding (SONPC) algorithm. The algorithm adapts online the neural population encoding of sensory and motor coordinates of a robot according to the underlying data distribution. By allocating more neurons towards area of sensory or motor space which are more frequently visited, this representation improves the accuracy of a robot system on a visually guided reaching task. We also suggest a Mean Reflection method to solve the notorious border effect problem encountered with SOMs for the special case where the latent space and the data space dimensions are the same. {\textcopyright} 2011 IEEE.",

keywords = "robot vision, self-organising feature maps",

author = "Tao Zhou and Piotr Dudek and Shi, {Bertram E.}",

note = "selforganizing neural population coding;robotic visuomotor coordination;Kohonen self organizing map algorithm;robot system;visually guided reaching task;mean reflection method;border effect problem;; 2011 International Joint Conference on Neural Network, IJCNN 2011 ; Conference date: 01-07-2011",

year = "2011",

doi = "10.1109/IJCNN.2011.6033393",

language = "English",

isbn = "9781457710865",

pages = "1437--1444",

booktitle = "Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks",

url = "http://dx.doi.org/10.1109/IJCNN.2011.6033393",

}

Zhou, T, Dudek, P & Shi, BE 2011, Self-Organizing Neural Population Coding for improving robotic visuomotor coordination. in Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks. pp. 1437-1444, 2011 International Joint Conference on Neural Network, IJCNN 2011, San Jose, CA, 1/07/11. https://doi.org/10.1109/IJCNN.2011.6033393

TY - GEN

T1 - Self-Organizing Neural Population Coding for improving robotic visuomotor coordination

AU - Zhou, Tao

AU - Dudek, Piotr

AU - Shi, Bertram E.

N1 - selforganizing neural population coding;robotic visuomotor coordination;Kohonen self organizing map algorithm;robot system;visually guided reaching task;mean reflection method;border effect problem;

PY - 2011

Y1 - 2011

N2 - We present an extension of Kohonen's Self Organizing Map (SOM) algorithm called the Self Organizing Neural Population Coding (SONPC) algorithm. The algorithm adapts online the neural population encoding of sensory and motor coordinates of a robot according to the underlying data distribution. By allocating more neurons towards area of sensory or motor space which are more frequently visited, this representation improves the accuracy of a robot system on a visually guided reaching task. We also suggest a Mean Reflection method to solve the notorious border effect problem encountered with SOMs for the special case where the latent space and the data space dimensions are the same. © 2011 IEEE.

AB - We present an extension of Kohonen's Self Organizing Map (SOM) algorithm called the Self Organizing Neural Population Coding (SONPC) algorithm. The algorithm adapts online the neural population encoding of sensory and motor coordinates of a robot according to the underlying data distribution. By allocating more neurons towards area of sensory or motor space which are more frequently visited, this representation improves the accuracy of a robot system on a visually guided reaching task. We also suggest a Mean Reflection method to solve the notorious border effect problem encountered with SOMs for the special case where the latent space and the data space dimensions are the same. © 2011 IEEE.

KW - robot vision

KW - self-organising feature maps

U2 - 10.1109/IJCNN.2011.6033393

DO - 10.1109/IJCNN.2011.6033393

M3 - Conference contribution

SN - 9781457710865

SP - 1437

EP - 1444

BT - Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks

T2 - 2011 International Joint Conference on Neural Network, IJCNN 2011

Y2 - 1 July 2011

ER -

Self-Organizing Neural Population Coding for improving robotic visuomotor coordination

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this