Publications
금융권 유일의 연구 조직으로 다양한 신기술 영역에서 하나금융그룹의 위상을 높이고
세계적 권위의 학회에서 대외 성과를 달성하고 있습니다.
Papers
Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling
- 발행일
- 2020.05.14
- 발행기관
- IEEE(2020)
- 저자
- Heung-Chang Lee, Do-Guk Kim, Bohyung Han
- Link
- https://ieeexplore.ieee.org/document/9053197
초록
We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search. Our approach samples candidate models from the multinomial distribution over the policy vectors. The proposed technique improves the efficiency of architecture search significantly compared to the existing methods while achieving competitive classification accuracy and model compactness. Our policy vectors are easily interpretable throughout the training procedure, which allows analyzing the search progress and the identified architectures. Note that, on the contrary, the black-box characteristics of the conventional methods based on RNN controllers hamper understanding training progress in terms of policy parameter updates. Our experiments demonstrate the outstanding performance of our approach compared to the state-of-the-art techniques with a fraction of search cost.