Quick Search:

uzh logo
Browse by:
bullet
bullet
bullet
bullet

Zurich Open Repository and ArchiveĀ 

Burfoot, D; Lungarella, M; Kuniyoshi, Y (2008). Toward a theory of embodied statistical learning. In: 10th International Conference on Simulation of Adaptive Behavior, Osaka, Japan, 07 July 2008 - 12 July 2008, 270-278.

Full text not available from this repository.

Abstract

The purpose of this paper is to outline a new formulation of statistical learning that will be more useful and relevant to the field of robotics. The primary motivation for this new perspective is the mismatch between the form of data assumed by current statistical learning algorithms, and the form of data that is actually generated by robotic systems. Specifically, robotic systems generate a vast unlabeled data stream, while most current algorithms are designed to handle limited numbers of discrete, labeled, independent and identically distributed samples. We argue that there is only one meaningful unsupervised learning process that can be applied to a vast data stream: adaptive compression. The compression rate can be used to compare different techniques, and statistical models obtained through adaptive compression should also be useful for other tasks.

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
DDC:000 Computer science, knowledge & systems
Language:English
Event End Date:12 July 2008
Deposited On:05 Jan 2009 11:32
Last Modified:23 Nov 2012 14:09
Publisher:Springer
Series Name:Lecture Notes in Computer Science
Number:5040
ISBN:978-3-540-69133-4
Additional Information:The paper is published in Proceedings of the 10th International Conference on Simulation of Adaptive Behavior (SAB 2008), Osaka, Japan, July 7-12, 2008.
Publisher DOI:10.1007/978-3-540-69134-1_27
Citations:Google Scholarā„¢

Users (please log in): suggest update or correction for this item

Repository Staff Only: item control page