Evolving Deep Neural Networks

By Risto Miikkulainen, J. Liang, Jason Zhi Liang, Elliot Meyerson, Aditya Rawal, Daniel Fink, Olivier Francon, B. Raju, H. Shahrzad, Arshak Navruzyan and 2 more. 2017

962 citations recorded by the source corpus.

Abstract The success of deep learning depends on finding an architecture to fit the task. As deep learning has scaled up to more challenging tasks, the architectures have become difficult to design by hand. This paper proposes an automated method, CoDeepNEAT, for optimizing deep learning architectures through evolution. By extending existing neuroevolution methods to topology, components, and hyperparameters, this method achieves results comparable to best human designs in standard benchmarks in object recognition and language modeling. It also supports building a real-world application of automated image captioning on a magazine website. Given the anticipated increases in available computing power, evolution of deep networks is promising approach to constructing deep learning applications in the future.

Subfields: Artificial Intelligence, Optimization & Training, Neural Architecture Search & AutoML

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Quoc V. Le
  2. Yoshua Bengio
  3. Mohit Bansal
  4. Dacheng Tao
  5. Sergey Levine
  6. Jianfeng Gao
  7. Trevor Darrell
  8. Alan L. Yuille

In Optimization & Training

  1. Quoc V. Le
  2. Frank Hutter
  3. Alan L. Yuille
  4. Barret Zoph
  5. Song Han
  6. Hanxiao Liu
  7. Martin Wistuba
  8. Jonathon Shlens

In Neural Architecture Search & AutoML

  1. Frank Hutter
  2. Martin Wistuba
  3. Quoc V. Le
  4. Song Han
  5. Thomas Elsken
  6. Tejaswini Pedapati
  7. Arber Zela
  8. Jan Hendrik Metzen

Citations in the corpus