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, 7 July 2008 - 12 July 2008, 270-278.
Full text not available from this repository.
View at publisher
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|
|Event End Date:||12 July 2008|
|Deposited On:||05 Jan 2009 10:32|
|Last Modified:||30 Oct 2014 08:29|
|Series Name:||Lecture Notes in Computer Science|
|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.|
Users (please log in): suggest update or correction for this item
Repository Staff Only: item control page