- Numerical analysis
- Causal Inference
HMLasso™* Factor analysis technology
Unravel factors with complex interrelationships, even from among fragmented data.
- Accurately build regression models using sparse modeling, even with large volumes of missing data.
- Contributes to increasing yield and productivity at factories and plants with sampling inspections.
- Lasso with High Missing Rate
Applications
- Identify factors behind decreased yield in semiconductor plants.
- Can also be applied in factor analysis of failures and abnormalities in infrastructure and office equipment.
Benchmarks, strengths, and track record
- Results of joint research with Inter-University Research Institute Corporation, Research Organization of Information and Systems, Institute of Statistical Mathematics
- Estimation error reduced by approximately 41% compared to cutting-edge algorithm “CoCoLasso.”
Inquiries
Please include the title “Toshiba AI Technology Catalog: HMLasso Factor analysis technology” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.
References:
- M. Takada et al., “HMLasso: Lasso with High Missing Rate,” IJCAI 2019.
- M. Takada, “hmlasso,” R package, 2019. (The Comprehensive R Archive Network)
- Develop a machine learning algorithm (AI) to identify factors in the effects even when large volumes of data are missing
