1. $L_{2}$
regularization versus batch and weight normalization;laarhoven;arXiv 1706 05350,2017
2. Batch normalization: Accelerating deep network training by reducing internal covariate shift;ioffe;Proceedings of the 32nd Intl Conf on Machine Learning,2015
3. Active learning: A survey;aggarwal;Data Classif Algorithms Appl,2014
4. Computational Analysis of Sound Scenes and Events
5. DropOut: A simple way to prevent neural networks from overfitting;nitish;J Mach Learn Res,2014