A DQN-Based Reinforcement Learning Model for Neural Network Architecture Search
碩士 === 國立中央大學 === 資訊管理學系 === 107 === Designing neural network (NN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modified from a handful of existing networks. We introduce HCM, a meta-modeling algorithm based on reinforcement l...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2019
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/qf2jk4 |
| Summary: | 碩士 === 國立中央大學 === 資訊管理學系 === 107 === Designing neural network (NN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modified from a handful of existing networks. We introduce HCM, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing NN architectures for a given learning task. The learning agent is trained to sequentially choose NN layers using DQN with an ɛ-greedy exploration strategy and experience replay. The agent explores a large but finite space of possible architectures and iteratively discovers designs with improved performance on the learning task. Even on image classification benchmarks, the agent-designed networks can do good as existing networks designed but more efficient. We also outperform existing meta-modeling approaches for network design on image classification or regression tasks.
|
|---|