1. An integral representation of functions using three-layered betworks and their approximation bounds;Murata;Neural Netw.,1996
2. Sampling hidden parameters from oracle distribution;Sonoda,2014
3. Deep sparse rectifier neural networks;Glorot,2011
4. Maxout networks;Goodfellow,2013
5. Improving deep neural networks for LVCSR using rectified linear units and dropout;Dahl,2013