论文标题
用简单方法对普通卷积神经网络的随机优化
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods
论文作者
论文摘要
在许多视觉模式分类问题中，卷积神经网络已经达到了最好的精度。但是，由于捕获此类表示所需的模型能力，它们通常对过度拟合过度敏感，因此需要适当的正则化以良好概括。在本文中，我们提出了正规化技术的结合，它们共同起作用以获得更好的性能，我们建立了普通的CNN，然后我们使用了数据增强，辍学和自定义的早期停止功能，我们通过在五个著名数据集上应用模型来测试和评估这些技术以及其他两个数据集的高准确性。
Convolutional neural networks have been achieving the best possible accuracies in many visual pattern classification problems. However, due to the model capacity required to capture such representations, they are often oversensitive to overfitting and therefore require proper regularization to generalize well. In this paper, we present a combination of regularization techniques which work together to get better performance, we built plain CNNs, and then we used data augmentation, dropout and customized early stopping function, we tested and evaluated these techniques by applying models on five famous datasets, MNIST, CIFAR10, CIFAR100, SVHN, STL10, and we achieved three state-of-the-art-of (MNIST, SVHN, STL10) and very high-Accuracy on the other two datasets.
