Genetic Optimisation of Training Sets for Improved Machine Learning Models of Molecular Properties
Nicholas J. Browning
Overview
Learning From Data
Types of Learning
The Kernel Method
Applications to Chemistry
Descriptors
Problem Outline
Database
Genetic Algorithms
Results & Discussion
Future Directions
Acknowledgements
Learning from Data
Regression
Classification
Clustering
Dimensionality Reduction
Application to Computational Chemistry
E(\{Z, R\}') = \sum_i{w}_i{\phi}_i(M_i(\{Z, R\}_i))
H\Psi = E\Psi
Made with Slides.com