Not logged in.
Quick Search - Contribution
Contribution Details
Type | Conference or Workshop Paper |
Scope | Discipline-based scholarship |
Published in Proceedings | Yes |
Title | Toward a theory of embodied statistical learning |
Organization Unit | |
Authors |
|
Editors |
|
Presentation Type | paper |
Item Subtype | Original Work |
Refereed | Yes |
Status | Published in final form |
Language |
|
ISBN | 978-3-540-69133-4 |
Page Range | 270 - 278 |
Event Title | 10th International Conference on Simulation of Adaptive Behavior |
Event Type | other |
Event Location | Osaka, Japan |
Event Start Date | July 7 - 2008 |
Event End Date | July 12 - 2008 |
Series Name | Lecture Notes in Computer Science |
Number | 5040 |
Place of Publication | Berlin |
Publisher | Springer |
Abstract Text | 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. |
Digital Object Identifier | 10.1007/978-3-540-69134-1_27 |
Other Identification Number | merlin-id:371 |
Export |
BibTeX
EP3 XML (ZORA) |
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. |