Impact of Training Set Batch Size on the Performance of Convolutional Neural Networks for Diverse Datasets 论文
2017Information Technology and Management Science引用 239
Neural Networks and ApplicationsAdvanced Neural Network ApplicationsAdversarial Robustness in Machine Learning
摘要
A problem of improving the performance of convolutional neural networks is considered. A parameter of the training set is investigated. The parameter is the batch size. The goal is to find an impact of training set batch size on the performance. To get consistent results, diverse datasets are used. They are MNIST and CIFAR-10. Simplicity of the MNIST dataset stands against complexity of the CIFAR-10 dataset, although the simpler dataset has 10 classes as well as the more complicated one.