1. Densely Connected Convolutional Networks
2. Adadelta: an adaptive learning rate method;zeiler;ArXiv Preprint,2012
3. Deep Residual Learning for Image Recognition
4. Stochas-tic gradient methods with block diagonal matrix adaptation;yun;ArXiv Preprint,2019
5. Adam: A method for stochastic optimization;kingma;ArXiv Preprint,2014