Share Email Print
cover

Proceedings Paper

Dimensionality reduction for sensorimotor learning in mobile robotics
Author(s): Daniel D. Lee
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Mobile robotic systems with a wide variety of sensors, actuators, and onboard high-speed processors are commercially and readily available. The information processing capabilities of these system presently lack the robustness and sophistication of biological systems. One challenge is that the high-dimensional input signals from the sensors need to be converted into a smaller number of perceptually relevant features. This dimensionality reduction can be performed on static signals such as a single image or on dynamic data such as a speech spectrogram. This proceedings discusses several different models for dimensionality reduction that differ only on the constraints on the variables and parameters of the models. In particular, nonnegativity constraints are shown to give rise to distributed yet sparse representations of both static and dynamic data.

Paper Details

Date Published: 6 December 2002
PDF: 7 pages
Proc. SPIE 4787, Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation V, (6 December 2002); doi: 10.1117/12.455856
Show Author Affiliations
Daniel D. Lee, Univ. of Pennsylvania (United States)


Published in SPIE Proceedings Vol. 4787:
Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation V
Bruno Bosacchi; David B. Fogel; James C. Bezdek, Editor(s)

© SPIE. Terms of Use
Back to Top