Evolutionary Reinforcement Learning for Automated Hyperparameter Optimization in EEG Classification

In recent years, deep learning (DL) methods have become one of the de-facto standard models for various EEG-based BCI tasks. However, it is well known that DL-based methods tend to be susceptible to hyperparameter settings and thus must be properly fine-tuned to provide reasonable performance. In spite of the importance of hyperparameter tuning, its optimization is often done by naive brute-force search methods that exhaustively evaluate all the possible candidates for each hyperparameter setting. To circumvent this problem, we propose to use population-based evolutionary search methods to solve the hyperparameter optimization problem dynamically and automatically without considerable human intervention. The main advantage of our method is that it only requires a single run of model for tuning process, as evolutionary search keeps track of past evaluation results and leverage this information to select the promising hyperparameter settings during training in an online manner. In the experiment, we apply the proposed method to optimize the hyperparameter sets of the EEGNet model on the BCI Competition IV-2a dataset and compare the results with the strong baseline model, which is the EEGNet fine-tuned by hand. The experimental results demonstrate the effectiveness of our proposed method by showing further improvement in mean accuracy up to 4.7% and 1.2% on the validation and the test sets, respectively.