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 2007.14166cs.LGstat.ML
收藏

深度学习的优化算法比较

A Comparison of Optimization Algorithms for Deep Learning

Mimar Sinan Fine Arts University(米马尔·希南美术大学)

Derya Soydaner

摘要:

近年来,我们见证了深度学习的兴起。深度神经网络已经在许多领域证明了它们的成功。然而,随着神经网络的深入和数据集的增大,这些网络的优化变得越来越困难。因此,在过去的几年中,已经提出了更先进的优化算法。在这项研究中,广泛使用的优化算法的深度学习进行了详细检查。为此,这些算法被称为自适应梯度方法的监督和无监督的任务。在训练过程中的算法的行为和结果的四个图像数据集,即MNIST,CIFAR-10,Kaggle花和标记的脸在野外进行比较,指出他们的差异对基本的优化算法。

英文摘要:

In recent years, we have witnessed the rise of deep learning. Deep neural networks have proved their success in many areas. However, the optimization of these networks has become more difficult as neural networks going deeper and datasets becoming bigger. Therefore, more advanced optimization algorithms have been proposed over the past years. In this study, widely used optimization algorithms for deep learning are examined in detail. To this end, these algorithms called adaptive gradient methods are implemented for both supervised and unsupervised tasks. The behaviour of the algorithms during training and results on four image datasets, namely, MNIST, CIFAR-10, Kaggle Flowers and Labeled Faces in the Wild are compared by pointing out their differences against basic optimization algorithms.

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。

↑