arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.02189cs.LGcs.AIcs.CV
收藏

使用此前未见的神经架构搜索数据集所得的洞见

Insights from the Use of Previously Unseen Neural Architecture Search Datasets

Newcastle University(纽卡斯尔大学);Durham University(杜伦大学);The Alan Turing Institute(艾伦·图灵研究所)

Rob Geada, David Towers, Matthew Forshaw, Amir Atapour-Abarghouei, A. Stephen McGough

AI总结:

针对NAS研究长期局限于少量代表性不足数据集的问题,本文发布八个面向NAS挑战赛的新未见数据集,并给出标准深度学习基线与参赛者最佳结果。

摘要:

可用于解决问题的神经网络具有无限可能性,而每种网络又有不同性能,这导致需要深度学习专家来识别最佳神经网络。这与消除专家需求的愿望相悖。神经架构搜索(NAS)通过自动识别最佳架构为此提供了解决方案。然而,迄今为止,NAS研究主要集中在少数数据集上,我们认为这些数据集不能代表现实世界问题。我们介绍了为一系列NAS挑战赛创建的八个新数据集:AddNIST、Language、MultNIST、CIFARTile、Gutenberg、Isabella、GeoClassing和Chesseract。开发这些数据集和挑战赛,是为了将注意力引向NAS开发中的问题,并鼓励研究者思考其模型在开发时未知的数据集上会有怎样的表现。我们展示了使用标准深度学习方法进行的实验,以及挑战赛参与者取得的最佳结果。

英文摘要:

The boundless possibility of neural networks which can be used to solve a problem -- each with different performance -- leads to a situation where a Deep Learning expert is required to identify the best neural network. This goes against the hope of removing the need for experts. Neural Architecture Search (NAS) offers a solution to this by automatically identifying the best architecture. However, to date, NAS work has focused on a small set of datasets which we argue are not representative of real-world problems. We introduce eight new datasets created for a series of NAS Challenges: AddNIST, Language, MultNIST, CIFARTile, Gutenberg, Isabella, GeoClassing, and Chesseract. These datasets and challenges are developed to direct attention to issues in NAS development and to encourage authors to consider how their models will perform on datasets unknown to them at development time. We present experimentation using standard Deep Learning methods as well as the best results from challenge participants.

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。

↑