Use H2O for ML in Python (or R).
Info regarding use of H2O: https://github.com/h2oai/h2o-3 Info regarding the dataset used in this exercise: https://www.kaggle.com/datasets/rwzhang/seeds-dataset
In many machine learning tasks, achieving a basic prediction with a default model is just the starting point. To ensure you get the most accurate results, it's crucial to fine-tune the model’s settings through hyperparameter optimization. This process involves adjusting parameters to enhance performance for a specific dataset or problem.
As a UCLL Applied Informatics student, you’ll explore a tool called 'h2o' to efficiently search for the best hyperparameter combinations. You'll apply methods such as grid search, random search, adaptive resampling, and AutoML to automate and refine the tuning process.
Throughout the course, you will work with just one dataset and experiment with a variety of supervised learning algorithms, including random forests, gradient boosting models, support vector machines, and neural networks. These hands-on exercises will prepare you to develop highly accurate and optimized machine learning solutions as you will apply and test them in your group work for the course 'Data Visualization and Analytics'.
Have fun!