This file is part of IDEAS, which uses RePEc data


[ Papers | Articles | Software | Books | Chapters | Authors | Institutions | JEL Classification | NEP reports | Search | New papers by email | Author registration | Rankings | Volunteers | FAQ | Blog | Help! ]

Information-Driven Organization Of Visual Receptive Fields

Author info | Abstract | Publisher info | Download info | Related research | Statistics
Author Info
CHRISTOPH SALGE () (Department of Computer Science, University of Hertfordshire, Hatfield, AL10 9AB, United Kingdom)
DANIEL POLANI () (Adaptive Systems Research Group, Computer Science, University of Hertfordshire, Hatfield, AL10 9AB, United Kingdom)
Abstract

By using information theory to reduce the state space of sensor arrays, such as receptive fields, for AI decision making we offer an adaptive algorithm without classical biases of hand coded approaches. This paper presents a way to build an acyclic directed graph to organize the sensor inputs of a visual receptive field. The Information Distance Metric is used to repeatedly select two sensors, which contain the most information about each other. Those are then encoded to a single variable, of equal alphabet size, with a deterministic mapping function that aims to create maximal entropy while maintaining a low information distance to the original sensors. The resulting tree determines which sensors are fused to reduce the input data while maintaining a maximum of information. The structure adapts to different environments of input images by encoding groups of preferred line structures or creating a higher resolution for areas with simulated movement. These effects are created without prior assumptions about the sensor statistics or the spatial configuration of the receptive field, and are cheap to compute since only pair-wise informational comparison of sensors is used.

Download Info
To download:

If you experience problems downloading a file, check if you have the proper application to view it first. Information about this may be contained in the File-Format links below. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.

File URL: http://www.worldscinet.com/cgi-bin/details.cgi?type=pdf&id=pii:S0219525909002234
File Format: application/pdf
File Function:
Download Restriction: Access to full text is restricted to subscribers.
File URL: http://www.worldscinet.com/cgi-bin/details.cgi?type=html&id=pii:S0219525909002234
File Format: text/html
File Function:
Download Restriction: Access to full text is restricted to subscribers.

As the access to this document is restricted, you may want to look for a different version under "Related research" (further below) or search for a different version of it.

Publisher Info
Article provided by World Scientific Publishing Co. Pte. Ltd. in its journal Advances in Complex Systems.

Volume (Year): 12 (2009)
Issue (Month): 03 ()
Pages: 311-326
Download reference. The following formats are available: HTML (with abstract), plain text (with abstract), BibTeX, RIS (EndNote, RefMan, ProCite), ReDIF
Handle: RePEc:wsi:acsxxx:v:12:y:2009:i:03:p:311-326

Contact details of provider:
Web page: http://www.worldscinet.com/acs/acs.shtml

Order Information:
Email:

For technical questions regarding this item, or to correct its listing, contact: (Tai Tone Lim).

Related research
Keywords: Information theory; adaptive sensors;

Statistics
Access and download statistics

Did you know? IDEAS also indexes software components.

This page was last updated on 2009-12-9.


This information is provided to you by IDEAS at the Department of Economics, College of Liberal Arts and Sciences, University of Connecticut using RePEc data on a server sponsored by the Society for Economic Dynamics.