Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net
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 develop...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2011-01-01
|
| Series: | Journal of Robotics |
| Online Access: | http://dx.doi.org/10.1155/2011/193146 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832561057186447360 |
|---|---|
| author | Soumi Ray Tim Oates |
| author_facet | Soumi Ray Tim Oates |
| author_sort | Soumi Ray |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-218438c8eb4441799eadce05f6c5e8f6 |
| institution | Kabale University |
| issn | 1687-9600 1687-9619 |
| language | English |
| publishDate | 2011-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Robotics |
| spelling | doaj-art-218438c8eb4441799eadce05f6c5e8f62025-02-03T01:26:03ZengWileyJournal of Robotics1687-96001687-96192011-01-01201110.1155/2011/193146193146Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-NetSoumi Ray0Tim Oates1Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, 1000 Hilltop Circle, Baltimore, MD 21250, USADepartment of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, 1000 Hilltop Circle, Baltimore, MD 21250, USATheoretical 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.http://dx.doi.org/10.1155/2011/193146 |
| spellingShingle | Soumi Ray Tim Oates Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net Journal of Robotics |
| title | Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net |
| title_full | Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net |
| title_fullStr | Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net |
| title_full_unstemmed | Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net |
| title_short | Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net |
| title_sort | discovering and characterizing hidden variables using a novel neural network architecture lo net |
| url | http://dx.doi.org/10.1155/2011/193146 |
| work_keys_str_mv | AT soumiray discoveringandcharacterizinghiddenvariablesusinganovelneuralnetworkarchitecturelonet AT timoates discoveringandcharacterizinghiddenvariablesusinganovelneuralnetworkarchitecturelonet |