Deep Learning as a Mixed Convex-Combinatorial Optimization Problem

international conference on learning representations, 2018.

Cited by: 13|Bibtex|Views34|Links
EI

Abstract:

As neural networks grow deeper and wider, learning networks with hard-threshold activations is becoming increasingly important, both for network quantization, which can drastically reduce time and energy requirements, and for creating large integrated systems of deep networks, which may have non-differentiable components and must avoid va...More

Code:

Data:

Your rating :
0

 

Tags
Comments