This project explores how hyperparameter autotuning can give you an extra edge in predictive power. This is a great tool to have in your toolbox if to try and get that bit more of accuracy you may need, especially when every point makes a major difference. The goal: create a machine learning model to discriminate between Higgs Boson particles vs. background noise in particle collisions from the Higgs Boson dataset.
Check out my blog about this project for all the details.
The environment used for this is SAS Viya Workbench.
For dependencies, see requirements.txt.
Whiteson, D. (2014). HIGGS [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5V312.
Baldi, P., Sadowski, P., & Whiteson, D. (2014, June 5). Searching for exotic particles in high-energy physics with Deep Learning. arXiv.org. https://arxiv.org/abs/1402.4735.