Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network
This addresses the problem of manual design in transfer CNNs for researchers, but it is incremental as it applies an existing optimization method to a specific task.
The paper tackled hyperparameter optimization for transfer convolutional neural networks by using a genetic algorithm to select trainable layers, achieving 97% precision on the Cats and Dogs dataset within 15 generations.
Hyperparameter optimization is a challenging problem in developing deep neural networks. Decision of transfer layers and trainable layers is a major task for design of the transfer convolutional neural networks (CNN). Conventional transfer CNN models are usually manually designed based on intuition. In this paper, a genetic algorithm is applied to select trainable layers of the transfer model. The filter criterion is constructed by accuracy and the counts of the trainable layers. The results show that the method is competent in this task. The system will converge with a precision of 97% in the classification of Cats and Dogs datasets, in no more than 15 generations. Moreover, backward inference according the results of the genetic algorithm shows that our method can capture the gradient features in network layers, which plays a part on understanding of the transfer AI models.