國立高雄大學圖資館 |

登入

回首頁

Machine learning-augmented spectroscopies for intelligent materials design

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Machine learning-augmented spectroscopies for intelligent materials designby Nina Andrejevic.
作者:	Andrejevic, Nina.
出版者:	Cham :Springer International Publishing :2022.
面頁冊數:	xii, 97 p. :ill. (chiefly color), digital ;24 cm.
附註:	"Doctoral thesis accepted by Massachusetts Institute of Technology, USA."
Contained By:	Springer Nature eBook
標題:	Smart materials.
電子資源:	https://doi.org/10.1007/978-3-031-14808-8
ISBN:	9783031148088$q(electronic bk.)

Machine learning-augmented spectroscopies for intelligent materials design
Andrejevic, Nina.

Machine learning-augmented spectroscopies for intelligent materials design[electronic resource] /by Nina Andrejevic. - Cham :Springer International Publishing :2022. - xii, 97 p. :ill. (chiefly color), digital ;24 cm. - Springer theses,2190-5061. - Springer theses..

"Doctoral thesis accepted by Massachusetts Institute of Technology, USA."

Chapter1: Introduction -- Chapter2: Background -- Chapter3: Data-efficient learning of materials' vibrational properties -- Chapter4: Machine learning-assisted parameter retrieval from polarized neutron reflectometry measurements -- Chapter5: Machine learning spectral indicators of topology -- Chapter6: Conclusion and outlook.

The thesis contains several pioneering results at the intersection of state-of-the-art materials characterization techniques and machine learning. The use of machine learning empowers the information extraction capability of neutron and photon spectroscopies. In particular, new knowledge and new physics insights to aid spectroscopic analysis may hold great promise for next-generation quantum technology. As a prominent example, the so-called proximity effect at topological material interfaces promises to enable spintronics without energy dissipation and quantum computing with fault tolerance, yet the characteristic spectral features to identify the proximity effect have long been elusive. The work presented within permits a fine resolution of its spectroscopic features and a determination of the proximity effect which could aid further experiments with improved interpretability. A few novel machine learning architectures are proposed in this thesis work which leverage the case when the data is scarce and utilize the internal symmetry of the system to improve the training quality. The work sheds light on future pathways to apply machine learning to augment experiments.

ISBN: 9783031148088$q(electronic bk.)

Standard No.: 10.1007/978-3-031-14808-8doiSubjects--Topical Terms:

184739
Smart materials.

LC Class. No.: TA418.9.S62

Dewey Class. No.: 620.112

Machine learning-augmented spectroscopies for intelligent materials design
LDR:02660nmm a2200349 a 4500 001 631647
003 DE-He213
005 20221006123922.0
006 m d
007 cr nn 008maaau
008 230411s2022 sz s 0 eng d
020 $a 9783031148088$q(electronic bk.)
020 $a 9783031148071$q(paper)
024 7 $a 10.1007/978-3-031-14808-8 $2 doi
035 $a 978-3-031-14808-8
040 $a GP $c GP
041 0 $a eng
050 4 $a TA418.9.S62
072 7 $a PNFS $2 bicssc
072 7 $a SCI078000 $2 bisacsh
072 7 $a PNFS $2 thema
082 0 4 $a 620.112 $2 23
090 $a TA418.9.S62 $b A559 2022
100 1 $a Andrejevic, Nina. $3 937512
245 1 0 $a Machine learning-augmented spectroscopies for intelligent materials design $h [electronic resource] / $c by Nina Andrejevic.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a xii, 97 p. : $b ill. (chiefly color), digital ; $c 24 cm.
490 1 $a Springer theses, $x 2190-5061
500 $a "Doctoral thesis accepted by Massachusetts Institute of Technology, USA."
505 0 $a Chapter1: Introduction -- Chapter2: Background -- Chapter3: Data-efficient learning of materials' vibrational properties -- Chapter4: Machine learning-assisted parameter retrieval from polarized neutron reflectometry measurements -- Chapter5: Machine learning spectral indicators of topology -- Chapter6: Conclusion and outlook.
520 $a The thesis contains several pioneering results at the intersection of state-of-the-art materials characterization techniques and machine learning. The use of machine learning empowers the information extraction capability of neutron and photon spectroscopies. In particular, new knowledge and new physics insights to aid spectroscopic analysis may hold great promise for next-generation quantum technology. As a prominent example, the so-called proximity effect at topological material interfaces promises to enable spintronics without energy dissipation and quantum computing with fault tolerance, yet the characteristic spectral features to identify the proximity effect have long been elusive. The work presented within permits a fine resolution of its spectroscopic features and a determination of the proximity effect which could aid further experiments with improved interpretability. A few novel machine learning architectures are proposed in this thesis work which leverage the case when the data is scarce and utilize the internal symmetry of the system to improve the training quality. The work sheds light on future pathways to apply machine learning to augment experiments.
650 0 $a Smart materials. $3 184739
650 0 $a Machine learning. $3 188639
650 0 $a Spectrum analysis. $3 188665
650 1 4 $a Spectroscopy. $3 737192
650 2 4 $a Electronic Devices. $3 913118
650 2 4 $a Machine Learning. $3 833608
650 2 4 $a Surfaces, Interfaces and Thin Film. $3 920202
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Springer theses. $3 557607
856 4 0 $u https://doi.org/10.1007/978-3-031-14808-8
950 $a Physics and Astronomy (SpringerNature-11651)