A Brute-Force CNN Model Selection for Accurate Classification of Sensorimotor Rhythms in BCIs.
Berdakh AbibullaevIrina DolzhikovaAmin ZollanvariPublished in: IEEE Access (2020)
Keyphrases
- model selection
- brute force
- accurate classification
- brain computer interface
- feature selection
- cross validation
- classification accuracy
- supervised learning
- classification algorithm
- signal processing
- computationally expensive
- hyperparameters
- mixture model
- machine learning
- exhaustive search
- selection criterion
- mutual information
- marginal likelihood
- generalization error
- bayesian methods
- feature set
- model selection criteria
- information criterion
- bayesian information criterion
- image processing
- gaussian process
- training data
- neural network
- face recognition
- training set
- automatic model selection