Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach
arXiv:2005.07669 · doi:10.1109/CEC48606.2020.9185856
Abstract
Efficient identification of people and objects, segmentation of regions of interest and extraction of relevant data in images, texts, audios and videos are evolving considerably in these past years, which deep learning methods, combined with recent improvements in computational resources, contributed greatly for this achievement. Although its outstanding potential, development of efficient architectures and modules requires expert knowledge and amount of resource time available. In this paper, we propose an evolutionary-based neural architecture search approach for efficient discovery of convolutional models in a dynamic search space, within only 24 GPU hours. With its efficient search environment and phenotype representation, Gene Expression Programming is adapted for network's cell generation. Despite having limited GPU resource time and broad search space, our proposal achieved similar state-of-the-art to manually-designed convolutional networks and also NAS-generated ones, even beating similar constrained evolutionary-based NAS works. The best cells in different runs achieved stable results, with a mean error of 2.82% in CIFAR-10 dataset (which the best model achieved an error of 2.67%) and 18.83% for CIFAR-100 (best model with 18.16%). For ImageNet in the mobile setting, our best model achieved top-1 and top-5 errors of 29.51% and 10.37%, respectively. Although evolutionary-based NAS works were reported to require a considerable amount of GPU time for architecture search, our approach obtained promising results in little time, encouraging further experiments in evolutionary-based NAS, for search and network representation improvements.
arXiv commentAccepted for presentation at the IEEE Congress on Evolutionary Computation (IEEE CEC) 2020
References in corpus (17)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Neural Architecture Search with Reinforcement Learning
- Improved Regularization of Convolutional Neural Networks with Cutout
- Gene Expression Programming: a New Adaptive Algorithm for Solving Problems
- Wide Residual Networks
- Neural Architecture Search: A Survey
- SGDR: Stochastic Gradient Descent with Warm Restarts
- AutoAugment: Learning Augmentation Policies from Data
- FractalNet: Ultra-Deep Neural Networks without Residuals
- Large-Scale Evolution of Image Classifiers
- PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
- Hierarchical Representations for Efficient Architecture Search
- Simple And Efficient Architecture Search for Convolutional Neural Networks
- Convolutional Neural Fabrics
- Progressive Neural Architecture Search
- NAS evaluation is frustratingly hard