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 2207.03757cs.LGcs.CV
收藏

将深度学习与优秀的老式机器学习相结合

Combining Deep Learning with Good Old-Fashioned Machine Learning

Ben-Gurion University(本-古里安大学)

Moshe Sipper

摘要:

我们提出了一个全面的,基于堆栈的框架,用于将深度学习与优秀的老式机器学习相结合,称为Deep GOLD。我们的框架涉及从51个重新训练的预训练深度网络中进行集成选择作为第一级模型,并将10个机器学习算法作为第二级模型。在当今最先进的软件工具和硬件平台的支持下,Deep GOLD在四个图像分类数据集上进行测试时提供了一致的改进:Fashion MNIST,CIFAR10,CIFAR100和Tiny ImageNet。在120个实验中,除了10个实验外,Deep GOLD都提高了原始网络的性能。

英文摘要:

We present a comprehensive, stacking-based framework for combining deep learning with good old-fashioned machine learning, called Deep GOld. Our framework involves ensemble selection from 51 retrained pretrained deep networks as first-level models, and 10 machine-learning algorithms as second-level models. Enabled by today's state-of-the-art software tools and hardware platforms, Deep GOld delivers consistent improvement when tested on four image-classification datasets: Fashion MNIST, CIFAR10, CIFAR100, and Tiny ImageNet. Of 120 experiments, in all but 10 Deep GOld improved the original networks' performance.

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。

↑