MACHINE LEARNING METHOD AND MACHINE LEARNING SYSTEM INVOLVING DATA AUGMENTATION

摘要

The present invention relates to machine learning techniques with data augmentation capabilities. The machine learning method comprises the steps of (a) obtaining initial values of a hyperparameter and a hypernetwork parameter; (b) generating a first classification model parameter according to the hyperparameter and the hypernetwork parameter, and updating the hypernetwork parameter according to the classification result based on the first classification model parameter for the training sample; (c) generating a second classification model parameter according to the hyperparameter and the updated hypernetwork parameter, and updating the hyperparameter according to another classification result based on the second classification model parameter for the verification sample; and (d) repeating steps (b) and (c) to update the hypernetwork parameters and hyperparameters.