國立虎尾科技大學 |

Nonlinear Inference in Partially Observed Physical Systems and Deep Neural Networks.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Nonlinear Inference in Partially Observed Physical Systems and Deep Neural Networks./
作者:	Rozdeba, Paul J.
面頁冊數:	1 online resource (168 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-07(E), Section: B.
Contained By:	Dissertation Abstracts International79-07B(E).
標題:	Computational physics. -
電子資源:	click for full text (PQDT)
ISBN:	9780355593815

Nonlinear Inference in Partially Observed Physical Systems and Deep Neural Networks.
Rozdeba, Paul J.

Nonlinear Inference in Partially Observed Physical Systems and Deep Neural Networks. - 1 online resource (168 pages)

Source: Dissertation Abstracts International, Volume: 79-07(E), Section: B.

Thesis (Ph.D.)--University of California, San Diego, 2018.

Includes bibliographical references

The problem of model state and parameter estimation is a significant challenge in nonlinear systems. Due to practical considerations of experimental design, it is often the case that physical systems are partially observed, meaning that data is only available for a subset of the degrees of freedom required to fully model the observed system's behaviors and, ultimately, predict future observations. Estimation in this context is highly complicated by the presence of chaos, stochasticity, and measurement noise in dynamical systems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355593815Subjects--Topical Terms:

1181955
Computational physics.
Index Terms--Genre/Form:

554714
Electronic books.

Nonlinear Inference in Partially Observed Physical Systems and Deep Neural Networks.
LDR:03035ntm a2200385Ki 4500 001 920692
005 20181203094032.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780355593815
035 $a (MiAaPQ)AAI10743524
035 $a (MiAaPQ)ucsd:17143
035 $a AAI10743524
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Rozdeba, Paul J. $3 1195562
245 1 0 $a Nonlinear Inference in Partially Observed Physical Systems and Deep Neural Networks.
264 0 $c 2018
300 $a 1 online resource (168 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-07(E), Section: B.
500 $a Adviser: Henry D. I. Abarbanel.
502 $a Thesis (Ph.D.)--University of California, San Diego, 2018.
504 $a Includes bibliographical references
520 $a The problem of model state and parameter estimation is a significant challenge in nonlinear systems. Due to practical considerations of experimental design, it is often the case that physical systems are partially observed, meaning that data is only available for a subset of the degrees of freedom required to fully model the observed system's behaviors and, ultimately, predict future observations. Estimation in this context is highly complicated by the presence of chaos, stochasticity, and measurement noise in dynamical systems.
520 $a One of the aims of this dissertation is to simultaneously analyze state and parameter estimation in as a regularized inverse problem, where the introduction of a model makes it possible to reverse the forward problem of partial, noisy observation; and as a statistical inference problem using data assimilation to transfer information from measurements to the model states and parameters. Ultimately these two formulations achieve the same goal. Similar aspects that appear in both are highlighted as a means for better understanding the structure of the nonlinear inference problem.
520 $a An alternative approach to data assimilation that uses model reduction is then examined as a way to eliminate unresolved nonlinear gating variables from neuron models. In this formulation, only measured variables enter into the model, and the resulting errors are themselves modeled by nonlinear stochastic processes with memory.
520 $a Finally, variational annealing, a data assimilation method previously applied to dynamical systems, is introduced as a potentially useful tool for understanding deep neural network training in machine learning by exploiting similarities between the two problems.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computational physics. $3 1181955
650 4 $a Theoretical physics. $3 1180318
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0216
690 $a 0753
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, San Diego. $b Physics. $3 1180745
773 0 $t Dissertation Abstracts International $g 79-07B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10743524 $z click for full text (PQDT)