Hypothesis Learning in Automated Experiment : Application to Combinatorial Materials Libraries

© 2022 Wiley-VCH GmbH.

Bibliographische Detailangaben
Veröffentlicht in:Advanced materials (Deerfield Beach, Fla.). - 1998. - 34(2022), 20 vom: 04. Mai, Seite e2201345
1. Verfasser: Ziatdinov, Maxim A (VerfasserIn)
Weitere Verfasser: Liu, Yongtao, Morozovska, Anna N, Eliseev, Eugene A, Zhang, Xiaohang, Takeuchi, Ichiro, Kalinin, Sergei V
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:Advanced materials (Deerfield Beach, Fla.)
Schlagworte:Journal Article active learning combinatorial library ferroelectric hypothesis learning scanning probe microscopy
LEADER 01000naa a22002652 4500
001 NLM33810657X
003 DE-627
005 20231225235923.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1002/adma.202201345  |2 doi 
028 5 2 |a pubmed24n1126.xml 
035 |a (DE-627)NLM33810657X 
035 |a (NLM)35279893 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Ziatdinov, Maxim A  |e verfasserin  |4 aut 
245 1 0 |a Hypothesis Learning in Automated Experiment  |b Application to Combinatorial Materials Libraries 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 23.05.2022 
500 |a Date Revised 23.05.2022 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a © 2022 Wiley-VCH GmbH. 
520 |a Machine learning is rapidly becoming an integral part of experimental physical discovery via automated and high-throughput synthesis, and active experiments in scattering and electron/probe microscopy. This, in turn, necessitates the development of active learning methods capable of exploring relevant parameter spaces with the smallest number of steps. Here, an active learning approach based on conavigation of the hypothesis and experimental spaces is introduced. This is realized by combining the structured Gaussian processes containing probabilistic models of the possible system's behaviors (hypotheses) with reinforcement learning policy refinement (discovery). This approach closely resembles classical human-driven physical discovery, when several alternative hypotheses realized via models with adjustable parameters are tested during an experiment. This approach is demonstrated for exploring concentration-induced phase transitions in combinatorial libraries of Sm-doped BiFeO3 using piezoresponse force microscopy, but it is straightforward to extend it to higher-dimensional parameter spaces and more complex physical problems once the experimental workflow and hypothesis generation are available 
650 4 |a Journal Article 
650 4 |a active learning 
650 4 |a combinatorial library 
650 4 |a ferroelectric 
650 4 |a hypothesis learning 
650 4 |a scanning probe microscopy 
700 1 |a Liu, Yongtao  |e verfasserin  |4 aut 
700 1 |a Morozovska, Anna N  |e verfasserin  |4 aut 
700 1 |a Eliseev, Eugene A  |e verfasserin  |4 aut 
700 1 |a Zhang, Xiaohang  |e verfasserin  |4 aut 
700 1 |a Takeuchi, Ichiro  |e verfasserin  |4 aut 
700 1 |a Kalinin, Sergei V  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t Advanced materials (Deerfield Beach, Fla.)  |d 1998  |g 34(2022), 20 vom: 04. Mai, Seite e2201345  |w (DE-627)NLM098206397  |x 1521-4095  |7 nnns 
773 1 8 |g volume:34  |g year:2022  |g number:20  |g day:04  |g month:05  |g pages:e2201345 
856 4 0 |u http://dx.doi.org/10.1002/adma.202201345  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 34  |j 2022  |e 20  |b 04  |c 05  |h e2201345