Neural Architecture Search Benchmarks: Insights and Survey
Open Access
- 8 March 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 25217-25236
Abstract
Neural Architecture Search (NAS), a promising and fast-moving research field, aims to automate the architectural design of Deep Neural Networks (DNNs) to achieve better performance on the given task and dataset. NAS methods have been very successful in discovering efficient models for various Computer Vision, Natural Language Processing, etc. The major obstacles to the advancement of NAS techniques are the demand for large computation resources and fair evaluation of various search methods. The differences in training pipeline and setting make it challenging to compare the efficiency of two NAS algorithms. A large number of NAS Benchmarks to simulate the architecture evaluation in seconds have been released over the last few years to ease the computation burden of training neural networks and can aid in the unbiased assessment of different search methods. This paper provides an extensive review of several publicly available NAS Benchmarks in the literature. We provide technical details and a deeper understanding of each benchmark and point out future directions.Keywords
Funding Information
- Philip and Virginia Sproul Professorship;
- National Science Foundation at Iowa State University (MRI 1726447, MRI 2018594)
- Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility (DEAC02-06CH11357)
This publication has 81 references indexed in Scilit:
- A genetic programming approach to designing convolutional neural network architectures2017
- Deep Residual Learning for Image Recognition2016
- Predicting effects of noncoding variants with deep learning–based sequence modelNature Methods, 2015
- Librispeech: An ASR corpus based on public domain audio books2015
- Machine learning approaches for improving condition-based maintenance of naval propulsion plantsProceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 2014
- OpenMLACM SIGKDD Explorations Newsletter, 2014
- Building the Ninapro database: A resource for the biorobotics community2012
- 2D Image Registration in CT Images Using Radial Image Descriptors2011
- HMDB: the Human Metabolome DatabaseNucleic Acids Research, 2007
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998