SMASH: One-Shot Model Architecture Search through HyperNetworks

Andrew Brock, Theodore Lim, James Millar Ritchie, Nicholas J. Weston

Research output: Contribution to conferencePoster


Designing architectures for deep neural networks requires expert knowledge and substantial computation time. We propose a technique to accelerate architecture selection by learning an auxiliary HyperNet that generates the weights of a main model conditioned on that model's architecture. By comparing the relative validation performance of networks with HyperNet-generated weights, we can effectively search over a wide range of architectures at the cost of a single training run. To facilitate this search, we develop a flexible mechanism based on memory read-writes that allows us to define a wide range of network connectivity patterns, with ResNet, DenseNet, and FractalNet blocks as special cases. We validate our method (SMASH) on CIFAR-10 and CIFAR-100, STL-10, ModelNet10, and Imagenet32x32, achieving competitive performance with similarly-sized hand-designed networks.
Original languageEnglish
Publication statusPublished - May 2018
Event6th International Conference on Learning Representations 2018 - Vancouver Convention Center, Vancouver, Canada
Duration: 30 Apr 20183 May 2018
Conference number: 6


Conference6th International Conference on Learning Representations 2018
Abbreviated titleICLR 2018
Internet address


  • Deep Learning
  • Hypernetworks
  • Transfer leanring
  • Benchmarking

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'SMASH: One-Shot Model Architecture Search through HyperNetworks'. Together they form a unique fingerprint.

Cite this