Deep rectifier networks
University of Montreal / Université de MontréalImage classification
Deep rectifier networks is image classification model published by University of Montreal / Université de Montréal in 2011.
About Deep rectifier networks
While logistic sigmoid neurons are more biologically plausible than hyperbolic tangent neurons, the latter work better for training multi-layer neural networks. This paper shows that rectifying neurons are an even better model of biological neurons a
Details
- Provider
- University of Montreal / Université de Montréal
- Task
- Image classification
- Released
- 2011-04-13