Method and device for processing experimental data by machine learning
JP2025505033APending Publication Date: 2025-02-19COMMISSARIAT A LENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- JP2024547291
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-02-09
- Filing Date
- 2023-02-09
- Publication Date
- 2025-02-19
Smart Images
Figure 2025505033000001_ABST
Abstract
The present invention relates to a method for characterizing a solid (4) comprising atoms and containing one or more defects, the method comprising: d ), comprising: d ) is obtained from at least one sensor (40) and has a multimodal distribution, the method comprising: - one or more reference individuals and said data, from 10 to 10 8 a representation of the dimension K included between - the solid to be characterized (4 d ) for at least a portion of the atoms; - classifying atoms of the structure according to their experimental confidence scores.
Need to check novelty before this filing date? Find Prior Art