• Corpus ID: 231740765

Importance of feature engineering and database selection in a machine learning model: A case study on carbon crystal structures

@article{Rohrhofer2021ImportanceOF,
  title={Importance of feature engineering and database selection in a machine learning model: A case study on carbon crystal structures},
  author={Franz M. Rohrhofer and Santanu Saha and Simone di Cataldo and Bernhard C. Geiger and Wolfgang von der Linden and Lilia Boeri},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.00191}
}
Franz M. Rohrhofer,1, 2 Santanu Saha,1, ∗ Simone Di Cataldo,1, 3 Bernhard C. Geiger,2 Wolfgang von der Linden,1 and Lilia Boeri3 Institute of Theoretical and Computational Physics, Graz University of Technology, NAWI Graz, 8010 Graz, Austria Know-Center GmbH, Research Center for Data-Driven Business & Big Data Analytics, Inffeldgasse 13, 8010 Graz, Austria Dipartimento di Fisica, Università di Roma La Sapienza, Piazzale Aldo Moro 5, I-00185 Roma, Italy (Dated: February 2, 2021) 
2 Citations
A Meta-Modeling Power Consumption Forecasting Approach Combining Client Similarity and Causality
TLDR
This study exploited the combined effects of client similarity and causality, and developed a power consumption forecasting model that utilizes ensembles of long short-term memory (LSTM) networks that resulted in more performant models when compared to implementations utilizing only one element on the same model structure.
Predicting polarizabilities of silicon clusters using local chemical environments
Calculating polarizabilities of large clusters with first-principles techniques is challenging because of the unfavorable scaling of computational cost with cluster size. To address this challenge,

References

SHOWING 1-3 OF 3 REFERENCES
Distribution of structures of MHM(blue), RS(yellow) and MHM+RS(red) for different SGD features 2 Y
  • Drug discovery today
  • 2018
Chem ( 2020 ) . 6 J . Behler
  • The Journal of chemical physics
Drug discovery today 23 , 1538 ( 2018 ) . 3 J . R . Kitchin
  • Nature Catalysis