- Home
- Research
- Scientific Machine Learning
Research
Scientific Machine Learning
What is Scientific Machine Learning (SciML)?
- Scientific machine learning** (SciML) is an emerging discipline within the data science community.
- SciML seeks to address domain-specic data challenges and extract insights from scientific data sets through innovative methodological solutions.
** we borrow the defitniion of SciML from https://www.osti.gov/biblio/1478744/
Transfer Learning (TL)?
- Leverage the knowledge of the pre-trianed ML model on the training of the target ML model with a sparse dataset
Unified TL approach (PaPIR)
- We introduced a unified transfer learning approach that both controls the amount of knowledge transferred to the target task as an initialization and regularization
- Partial transfer learning outperforms the baseline TL approach when the task similarity between the source and target tasks are pronounced.
- We utilized a Hessian matrix as a weighting function for TL, showing a significant performance gain compared to the baseline TL method
