Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture : LO-Net
Joint Authors
Source
Issue
Vol. 2011, Issue 2011 (31 Dec. 2011), pp.1-16, 16 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2012-01-03
Country of Publication
Egypt
No. of Pages
16
Main Subjects
Abstract EN
Theoretical entities are aspects of the world that cannot be sensed directly but that, nevertheless, are causally relevant.
Scientific inquiry has uncovered many such entities, such as black holes and dark matter.
We claim that theoretical entities, or hidden variables, are important for the development of concepts within the lifetime of an individual and present a novel neural network architecture that solves three problems related to theoretical entities: (1) discovering that they exist, (2) determining their number, and (3) computing their values.
Experiments show the utility of the proposed approach using discrete time dynamical systems, in which some of the state variables are hidden, and sensor data obtained from the camera of a mobile robot, in which the sizes and locations of objects in the visual field are observed but their sizes and locations (distances) in the three-dimensional world are not.
Two different regularization terms are explored that improve the network's ability to approximate the values of hidden variables, and the performance and capabilities of the network are compared to that of Hidden Markov Models.
American Psychological Association (APA)
Ray, Soumi& Oates, Tim. 2012. Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture : LO-Net. Journal of Robotics،Vol. 2011, no. 2011, pp.1-16.
https://search.emarefa.net/detail/BIM-453393
Modern Language Association (MLA)
Ray, Soumi& Oates, Tim. Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture : LO-Net. Journal of Robotics No. 2011 (2011), pp.1-16.
https://search.emarefa.net/detail/BIM-453393
American Medical Association (AMA)
Ray, Soumi& Oates, Tim. Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture : LO-Net. Journal of Robotics. 2012. Vol. 2011, no. 2011, pp.1-16.
https://search.emarefa.net/detail/BIM-453393
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-453393