Data-Driven Sparse Structure Selection for Deep Neural Networks

@article{Huang2017DataDrivenSS,
  title={Data-Driven Sparse Structure Selection for Deep Neural Networks},
  author={Zehao Huang and Naiyan Wang},
  journal={CoRR},
  year={2017},
  volume={abs/1707.01213}
}
Deep convolutional neural networks have liberated its extraordinary power on various tasks. However, it is still very challenging to deploy state-of-the-art models into real-world applications due to their high computational complexity. How can we design a compact and effective network without massive experiments and expert knowledge? In this paper, we… CONTINUE READING