1. Improving cur matrix decomposition and the Nyström approximation via adaptive sampling;wang;J Mach Learn Res,2013
2. Scaling learning algorithms towards AI;bengio;Large Scale Kernel Machines,2007
3. Understanding the difficulty of training deep feedforward neural networks;glorot;Proc 13th Int Conf Artif Intell Statist Workshop Conf,0
4. Predicting parameters in deep learning;denil;Proc NIPS,0