Open coranholmes opened 6 years ago
The hyper-parameters were selected from running a random hyper-parameter search with sobol sequence.
Finding hyper-parameters is one of the hardest parts of machine learning. I suggest you google and learn about the various types of optimization.
May I ask if there is a place where the optimal model is saved after using the sobol sequence search?
The hyper parameters used for the experiments are already set. May I ask how are the current hyper parameters selected? Are there any tips for selecting hyper parameters to get better experimental results (using the datasets included under experiments folder)?