在动态搜索空间中利用有限GPU时间优化神经架构搜索：一种基因表达式编程方法
Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach
AI总结：
本文提出一种基于基因表达式编程的进化式神经架构搜索方法，在动态搜索空间和仅24个GPU小时的限制下高效发现卷积模型，并在CIFAR和ImageNet上取得与人工设计及NAS生成网络相当的先进结果。
摘要：
近年来，对人物和物体的高效识别、感兴趣区域的分割以及图像、文本、音频和视频中相关数据的提取正在迅速发展，深度学习方法与计算资源的最新改进为这一成就做出了巨大贡献。尽管其潜力巨大，但高效架构和模块的开发仍需要专家知识和大量可用资源时间。在本文中，我们提出了一种基于进化的神经架构搜索方法，用于在动态搜索空间中高效发现卷积模型，且仅需24个GPU小时。凭借其高效的搜索环境和表型表示，基因表达式编程被适配用于网络单元生成。尽管GPU资源时间有限且搜索空间广阔，我们的方法取得了与人工设计的卷积网络以及NAS生成网络相似的当前最优水平，甚至优于类似的受约束进化式NAS工作。不同运行中的最佳单元取得了稳定结果，在CIFAR-10数据集上平均错误率为2.82%（最佳模型错误率为2.67%），在CIFAR-100上为18.83%（最佳模型为18.16%）。对于移动设置下的ImageNet，我们的最佳模型分别取得了29.51%的top-1错误率和10.37%的top-5错误率。尽管据报道进化式NAS工作需要大量GPU时间进行架构搜索，但我们的方法在短时间内取得了有前景的结果，鼓励在进化式NAS中进一步开展实验，以改进搜索和网络表示。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
