Title:
LEARNING DEVICE, INFERENCE DEVICE, AND MODEL CREATION METHOD
Document Type and Number:
WIPO Patent Application WO/2024/034688
Kind Code:
A1
Abstract:
A learning device (1) according to an embodiment of the present invention comprises: at least one memory (33, 35); and at least one processor (31). The at least one processor (31): acquires teacher data of a physical parameter; inputs the teacher data into a first model to generate a potential function; uses the potential function to output a first value of the physical parameter; and on the basis of the first value of the physical parameter and the teacher data, adjusts a network parameter of the first model.
Inventors:
ONO SEISHIRO (JP)
KURATA IORI (JP)
TAKAMOTO SO (JP)
KURATA IORI (JP)
TAKAMOTO SO (JP)
Application Number:
PCT/JP2023/029372
Publication Date:
February 15, 2024
Filing Date:
August 10, 2023
Export Citation:
Assignee:
PREFERRED NETWORKS INC (JP)
International Classes:
G06N20/00; G06N3/06
Domestic Patent References:
| WO2020049994A1 | 2020-03-12 | |||
| WO2021054402A1 | 2021-03-25 |
Foreign References:
| JP2021189473A | 2021-12-13 | |||
| JP2019036207A | 2019-03-07 |
Other References:
HIROKAWA YUTA, MASASHI NODA, SHUNSUKE YAMADA, ATSUSHI YAMADA : "Optimization and performance evaluation of electrodynamics application SALMON for supercomputer "Fugaku"", IPSJ SIG TECHNICAL REPORTS, INFORMATION PROCESSING SOCIETY OF JAPAN, JP, vol. 2020-HPC-173, no. 4, 16 March 2020 (2020-03-16), JP , pages 1 - 9, XP093139394, ISSN: 2188-8841
BROCKHERDE FELIX, VOGT LESLIE, LI LI, TUCKERMAN MARK E., BURKE KIERON, MÜLLER KLAUS-ROBERT: "Bypassing the Kohn-Sham equations with machine learning", NATURE COMMUNICATIONS, NATURE PUBLISHING GROUP, UK, vol. 8, no. 1, UK, XP093139398, ISSN: 2041-1723, DOI: 10.1038/s41467-017-00839-3
BROCKHERDE FELIX, VOGT LESLIE, LI LI, TUCKERMAN MARK E., BURKE KIERON, MÜLLER KLAUS-ROBERT: "Bypassing the Kohn-Sham equations with machine learning", NATURE COMMUNICATIONS, NATURE PUBLISHING GROUP, UK, vol. 8, no. 1, UK, XP093139398, ISSN: 2041-1723, DOI: 10.1038/s41467-017-00839-3
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: