基于改进贝叶斯优化算法的CNN超参数优化方法

In the framework of convolutional neural network (CNN) , how to obtain the hyper-parameters of its model automatically is an important and pressing research topic. In this paper, we proposed a hyper-parameter optimization method of CNN based on improved Bayesian optimization algorithm. This method uses the improved Thompson sampling method as the acquisition function. The improved Markov Chain Monte Carlo algorithm is used to accelerate the Gaussian surrogate model. The proposed method can be used to optimize hyper-parameters in frameworks of CNN with different hyper-parameter space. The performance of the algorithm was tested by using these testing sets: CIFAR-10, MRBI and SVHN. The experimental results show that the improved hyper-parameter optimization algorithm of CNN has better performance than the other algorithms.