-
Framework for benchmarking Hyperparameter Tuning techniques for Machine Learning use cases in manufacturing
-
Integrated HPO libraries: hpbandster, hyperopt, optuna, skopt, robo
-
Integrated HPO methods: Random Search, CMA-ES, Hyperband, GPBO, SMAC, TPE, BOHB, Fabolas, Bohamiann
-
Integrated ML algorithms: Random Forests, Neural Networks, SVM, XGBoost, AdaBoost, Linear Regression, K-Nearest Neighbors
-
Use Cases:
- Kaggle-Challenge: Predict sales prices and practice feature engineering, RFs, and gradient boosting (https://www.kaggle.com/c/house-prices-advanced-regression-techniques)
brunompacheco/HPO-benchmarking-framework
Framework for benchmarking Hyperparameter Tuning techniques for Machine Learning use cases in manufacturing
Python