Designing Neural Network Architectures using Reinforcement Learning

By Bowen Baker, Otkrist Gupta, Nikhil Naik, Ramesh Raskar. 2016

1,553 citations recorded by the source corpus.

At present, designing convolutional neural network (CNN) architectures requires both human expertise and labor. New architectures are handcrafted by careful experimentation or modified from a handful of existing networks. We introduce MetaQNN, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing CNN architectures for a given learning task. The learning agent is trained to sequentially choose CNN layers using $Q$-learning with an $\epsilon$-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. On image classification benchmarks, the agent-designed networks (consisting of only standard convolution, pooling, and fully-connected layers) beat existing networks designed with the same layer types and are competitive against the state-of-the-art methods that use more complex layer types. We also outperform existing meta-modeling approaches for network design on image classification tasks.

Subfields: Artificial Intelligence, Reinforcement Learning, 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. Mohit Bansal
  3. Yoshua Bengio
  4. Sergey Levine
  5. Dacheng Tao
  6. Jianfeng Gao
  7. Trevor Darrell
  8. Alan L. Yuille

In Reinforcement Learning

  1. Sergey Levine
  2. Pieter Abbeel
  3. Chelsea Finn
  4. Martin Wistuba
  5. Trevor Darrell
  6. Ruslan Salakhutdinov
  7. Igor Mordatch
  8. Abhishek Gupta

In Neural Architecture Search & AutoML

  1. Frank Hutter
  2. Martin Wistuba
  3. Quoc V. Le
  4. Xuanyi Dong
  5. Colin White
  6. Yash Savani
  7. Song Han
  8. Xia Hu

Citations in the corpus