Abstract
Straightforward, interpretable, and modifiable linear-regression prediction models with appropriate accuracy are constructed by sparse modeling coupled with our chemical perspectives as researchers on small data, such as experimental data in laboratories.
Highlights
In sparse modeling (SpM)-S, SpM is combined with our chemical perspectives for application to small data
The new data-scienti c approach was compared with other machine learning (ML) methods, such as least absolute shrinkage and selection operator (LASSO) and multiple linear regression (ML-rate of successful experiments (Rs)) for linear regression, and support vector regression (SV-R), random forest regression (RF-R), and neural network regression (NN-R) for nonlinear regression
The test datasets for the validation were prepared by the controlled synthesis of 2D materials under the predicted conditions
Summary
Machine learning (ML) on big data, such as deep learning, has been a powerful tool in our daily life.[1,2] In materials science, discovery of new materials, optimization of processes, and enhancement of performances have been achieved by datadriven methods.[3,4,5,6,7,8,9,10,11,12,13,14,15] In chemistry, new functional molecules and catalysts have been found using ML. While a well-trained predictor with high correlation between the estimated and actual values is prepared on small training data, the prediction accuracy lowers on unknown test data. A variety of small data have been le with development of arti cial intelligence. Experimental scientists have their own small data including successes and failures. If such small data is utilized by ML, research projects can be accelerated without wasting time, money, and effort. Speci c methods, such as transfer learning, are developed to address the lack of data.[21] additional data is eventually required to improve the prediction accuracy
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.