arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.13033cs.LGcs.NE
收藏

并行神经树和数据预处理AutoML用于图像分类

Concurrent Neural Tree and Data Preprocessing AutoML for Image Classification

Institute for Clarity in Documentation(文档清晰度研究所);Inria Paris-Rocquencourt(法国国家信息与自动化研究所巴黎-罗克库尔中心);Rajiv Gandhi University(拉吉夫·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕尔默研究实验室);Georgia Institute of Technology(佐治亚理工学院);Georgia Tech Research Institute(佐治亚理工研究院)

Anish Thite, Mohan Dodda, Pulak Agarwal, Jason Zutty

摘要:

深度神经网络(DNN)是一种广泛用于各种机器学习问题的解决方案。然而,数据科学家通常需要投入大量的时间来预处理输入数据,测试不同的神经网络架构,并调整超参数以获得最佳性能。自动机器学习(autoML)方法自动搜索最佳神经网络的架构和超参数空间。然而,当前最新技术水平(SOTA)方法不包括用于操纵输入数据作为算法搜索空间的一部分的传统方法。我们适应进化多目标算法设计引擎(EMADE),多目标进化搜索框架的传统机器学习方法,执行神经结构搜索。我们还集成了EMADE的信号处理和图像处理原语。这些原语允许EMADE在摄取到同时进化的DNN之前操纵输入数据。我们表明,包括这些方法作为搜索空间的一部分,显示出潜在的CIFAR-10图像分类基准数据集上的性能提供的好处。

英文摘要:

Deep Neural Networks (DNN's) are a widely-used solution for a variety of machine learning problems. However, it is often necessary to invest a significant amount of a data scientist's time to pre-process input data, test different neural network architectures, and tune hyper-parameters for optimal performance. Automated machine learning (autoML) methods automatically search the architecture and hyper-parameter space for optimal neural networks. However, current state-of-the-art (SOTA) methods do not include traditional methods for manipulating input data as part of the algorithmic search space. We adapt the Evolutionary Multi-objective Algorithm Design Engine (EMADE), a multi-objective evolutionary search framework for traditional machine learning methods, to perform neural architecture search. We also integrate EMADE's signal processing and image processing primitives. These primitives allow EMADE to manipulate input data before ingestion into the simultaneously evolved DNN. We show that including these methods as part of the search space shows potential to provide benefits to performance on the CIFAR-10 image classification benchmark dataset.

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。

↑