FASTANDACCURATEDEEPNETWORKLEARNINGBYEXPONENTIALLINEARUNITSELUS FAST AND ACCURATE DEEP NETWORK LEARNING BY EXPONENTIAL LINEAR UNITS (ELUS)(2016,Djork-Arn´e Clevert, Thomas Unterthiner & Sepp Hochreiter)
Batch Normalization Accelerating Deep Network Training by Reducing Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift