Journal
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
Volume 25, Issue 2, Pages 277-291Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TEVC.2020.3024708
Keywords
Computer architecture; Optimization; Search problems; Task analysis; Neural networks; Computational modeling; Graphics processing units; Convolutional neural networks (CNNs); evolutionary deep learning; genetic algorithms (GAs); neural architecture search (NAS)
Funding
- National Science Foundation [DBI-0939454]
Ask authors/readers for more resources
This study proposes an evolutionary algorithm for searching neural architectures, which fills a set of architectures through genetic operations to approximate the entire Pareto frontier, improves computational efficiency, and reinforces shared patterns among past successful architectures through Bayesian model learning. The method achieves competitive performance in image classification tasks, while considering multiple objectives.
Convolutional neural networks (CNNs) are the backbones of deep learning paradigms for numerous vision tasks. Early advancements in CNN architectures are primarily driven by human expertise and by elaborate design processes. Recently, neural architecture search was proposed with the aim of automating the network design process and generating task-dependent architectures. While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: 1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario and 2) the search process requires vast computational resources in most approaches. To overcome these limitations, we propose an evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating point operations (FLOPs). The proposed method addresses the first shortcoming by populating a set of architectures to approximate the entire Pareto frontier through genetic operations that recombine and modify architectural components progressively. Our approach improves computational efficiency by carefully down-scaling the architectures during the search as well as reinforcing the patterns commonly shared among past successful architectures through Bayesian model learning. The integration of these two main contributions allows an efficient design of architectures that are competitive and in most cases outperform both manually and automatically designed architectures on benchmark image classification datasets: CIFAR, ImageNet, and human chest X-ray. The flexibility provided from simultaneously obtaining multiple architecture choices for different compute requirements further differentiates our approach from other methods in the literature.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available