2338704 results
Sort by:
In: PS, Volume 18, Issue 4, p. 939-968
ISSN: 2325-7172
In: The journal of politics: JOP, Volume 46, Issue 4, p. 1281-1284
ISSN: 1468-2508
In: Soviet studies, Volume 36, Issue 3, p. 317-344
In: PS, Volume 17, Issue 4, p. 934-960
ISSN: 2325-7172
In: Government & opposition: an international journal of comparative politics, Volume 18, p. 194-217
ISSN: 0017-257X
In: Women & politics: a quarterly journal of research and policy studies, Volume 1, Issue 1, p. 111-113
ISSN: 1540-9473
In: PS, Volume 5, Issue 4, p. 436-438
ISSN: 2325-7172
In: Problems and Methods in the Study of Politics, p. 186-200
In: The journal of politics: JOP, Volume 28, Issue 2, p. 486-487
ISSN: 1468-2508
In: International affairs, Volume 28, Issue 2, p. 275-275
ISSN: 1468-2346
This paper discusses the application of the virtual reference tuning (VRT) techniques to tune neural controllers from batch inputoutput data, by particularising nonlinear VRT and suitably computing gradients backpropagating in time. The flexibility of gradient computation with neural networks also allows alternative block diagrams with extra inputs to be considered. The neural approach to VRT in a closed-loop setup is compared to the linear VRFT one in a simulated crane example. © 2011 Elsevier Ltd. All rights reserved. ; A. Esparza is grateful to the project GVPRE/2008/116 financed by Generalitat Valenciana. The authors are also grateful to the financial support of Grants dpi2008-06731-c02-01, dpi2011-27845-c02-01 (Spanish Government) and prometeo/2008/088 (Generalitat Valenciana). ; Esparza Peidro, A.; Sala, A.; Albertos Pérez, P. (2011). Neural networks in virtual reference tuning. Engineering Applications of Artificial Intelligence. 24(6):983-995. https://doi.org/10.1016/j.engappai.2011.04.003 ; S ; 983 ; 995 ; 24 ; 6
BASE
In: Australian journal of political science: journal of the Australasian Political Studies Association, Volume 45, Issue 3, p. 475-481
ISSN: 1363-030X
983 995 24 6 ; S ; This paper discusses the application of the virtual reference tuning (VRT) techniques to tune neural controllers from batch inputoutput data, by particularising nonlinear VRT and suitably computing gradients backpropagating in time. The flexibility of gradient computation with neural networks also allows alternative block diagrams with extra inputs to be considered. The neural approach to VRT in a closed-loop setup is compared to the linear VRFT one in a simulated crane example. © 2011 Elsevier Ltd. All rights reserved. A. Esparza is grateful to the project GVPRE/2008/116 financed by Generalitat Valenciana. The authors are also grateful to the financial support of Grants dpi2008-06731-c02-01, dpi2011-27845-c02-01 (Spanish Government) and prometeo/2008/088 (Generalitat Valenciana). Esparza Peidro, A.; Sala, A.; Albertos Pérez, P. (2011). Neural networks in virtual reference tuning. Engineering Applications of Artificial Intelligence. 24(6):983-995. doi:10.1016/j.engappai.2011.04.003
BASE
SSRN
In: Synthese Library, Studies in Epistemology, Logic, Methodology, and Philosophy of Science 490
Preface -- 1. On Arbitrary Reference -- 2. On Plural Arbitrary Reference -- 3. On Arbitrary Fictional Models -- 4. Second-Order Logic and Plural Arbitrary Reference -- 5. Logical Concepts and Plural Arbitrary Reference -- 6. Plural Arbitrary Reference and mereology -- 7. Grounding Megethology on Plural Arbitrary Reference -- 8. The Mereological foundation of Megethology -- 9. Final ruminations -- Index.