arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.02549cs.LGcs.CVstat.ML
收藏

测量深度学习方法的数据效率

Measuring the Data Efficiency of Deep Learning Methods

Ruhr University Bochum(波鸿鲁尔大学)

Hlynur Davíð Hlynsson, Alberto N. Escalante-B., Laurenz Wiskott

摘要:

在本文中,我们提出了一个新的实验协议,并使用它来基准测试两种深度学习算法,卷积神经网络(CNN)和分层信息保持基于图的慢特征分析(HiGSFA)的数据效率-性能作为训练集大小的函数,用于分类和迁移学习场景中的任务。这些算法在MNIST和Omniglot数据集的不同大小的子集上进行训练。HiGSFA优于标准的CNN网络,当模型在每个类别50和200个样本上进行MNIST分类训练时。在其他情况下,CNN表现更好。结果表明,在某些情况下,贪婪的局部最优自下而上学习与全局基于梯度的学习一样或更强大。

英文摘要:

In this paper, we propose a new experimental protocol and use it to benchmark the data efficiency --- performance as a function of training set size --- of two deep learning algorithms, convolutional neural networks (CNNs) and hierarchical information-preserving graph-based slow feature analysis (HiGSFA), for tasks in classification and transfer learning scenarios. The algorithms are trained on different-sized subsets of the MNIST and Omniglot data sets. HiGSFA outperforms standard CNN networks when the models are trained on 50 and 200 samples per class for MNIST classification. In other cases, the CNNs perform better. The results suggest that there are cases where greedy, locally optimal bottom-up learning is equally or more powerful than global gradient-based learning.

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。

↑