Search Tree Pruning for Progressive Neural Architecture Search (Student Abstract)

Authors

  • Deanna Flynn University of Alaska Anchorage
  • P. Michael Furlong NASA Ames Research Center
  • Brian Coltin NASA Ames Research Center

DOI:

https://doi.org/10.1609/aaai.v34i10.7163

Abstract

Our neural architecture search algorithm progressively searches a tree of neural network architectures. Child nodes are created by inserting new layers determined by a transition graph into a parent network up to a maximum depth and pruned when performance is worse than its parent. This increases efficiency but makes the algorithm greedy. Simpler networks are successfully found before more complex ones that can achieve benchmark performance similar to other top-performing networks.

Downloads

Published

2020-04-03

How to Cite

Flynn, D., Furlong, P. M., & Coltin, B. (2020). Search Tree Pruning for Progressive Neural Architecture Search (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13783-13784. https://doi.org/10.1609/aaai.v34i10.7163

Issue

Section

Student Abstract Track