Deep-Learning Prediction Model with Serial Two-Level Decomposition Based on Bayesian Optimization
Algorithm 1
Sequential model-based optimization.
Input: is the root mean square error of the proposed model, is the number of selected hyperparameter groups, H is the UCB acquisition function, is the input data, is the proposed model, is the input hyperparameter group.
Output: returns the optimal hyperparameter group .
for to do
Model the objective function and calculate the posterior probability.
Parameter group selection using the UCB acquisition function.
Using superparameter group to train network to get the prediction