Dynamic Capacity Networks

  title={Dynamic Capacity Networks},
  author={Amjad Almahairi and Nicolas Ballas and Tim Cooijmans and Yin Zheng and Hugo Larochelle and Aaron C. Courville},
We introduce the Dynamic Capacity Network (DCN), a neural network that can adaptively assign its capacity across different portions of the input data. This is achieved by combining modules of two types: low-capacity sub-networks and high-capacity sub-networks. The low-capacity sub-networks are applied across most of the input, but also provide a guide to select a few portions of the input on which to apply the high-capacity sub-networks. The selection is made using a novel gradient-based… CONTINUE READING
Highly Cited
This paper has 32 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 30 times over the past 90 days. VIEW TWEETS
23 Citations
23 References
Similar Papers


Publications citing this paper.

Similar Papers

Loading similar papers…