An Introduction to Neural Architecture Search for Convolutional Networks
arXiv:2005.11074
Abstract
Neural Architecture Search (NAS) is a research field concerned with utilizing optimization algorithms to design optimal neural network architectures. There are many approaches concerning the architectural search spaces, optimization algorithms, as well as candidate architecture evaluation methods. As the field is growing at a continuously increasing pace, it is difficult for a beginner to discern between major, as well as emerging directions the field has followed. In this work, we provide an introduction to the basic concepts of NAS for convolutional networks, along with the major advances in search spaces, algorithms and evaluation techniques.
arXiv comment17 pages, 4 figures
References in corpus (15)
- An overview of gradient descent optimization algorithms
- Neural Architecture Search with Reinforcement Learning
- DARTS: Differentiable Architecture Search
- Neural Architecture Optimization
- A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
- Efficient Architecture Search by Network Transformation
- SNAS: Stochastic Neural Architecture Search
- NAS-Bench-101: Towards Reproducible Neural Architecture Search
- Simple And Efficient Architecture Search for Convolutional Neural Networks
- Path-Level Network Transformation for Efficient Architecture Search
- Graph HyperNetworks for Neural Architecture Search
- Playing FPS Games with Deep Reinforcement Learning
- Best Practices for Scientific Research on Neural Architecture Search
- Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search
- NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search