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.
翻译:在本文中,我们提出了一个新的实验协议,并用它来衡量数据效率 -- -- 业绩作为培训设置规模的函数 -- -- 即两个深层学习算法、进化神经网络和等级信息保存图的慢速特征分析(HISFA),用于分类和转移学习设想方案。算法在MNIST和Omniglot数据集不同规模子集方面得到了培训。HISFA在模型每类50和200个样本进行MNIST分类培训时,优于标准CNN网络。在其他情况下,CNN的表现更好。结果显示,贪婪、地方上最佳的自下而上学习比全球梯度学习同样或更强大。