Deep learning from a statistical perspective
Deep learning from a statistical perspective
复制标题
DOI：
10.1002/sta4.294
复制
发表时间：
2020-01
期刊：
影响因子：
1.7
通讯作者：
Yubai Yuan;Yujia Deng;Yanqing Zhang;A. Qu
中科院分区：
文献类型：
--
作者：
Yubai Yuan;Yujia Deng;Yanqing Zhang;A. Qu
作为发展最快的人工智能技术之一，深度学习已应用于各种机器学习任务，并在数据科学和统计学领域受到高度关注。不管模型结构如何复杂，深度神经网络都可以被视为现有统计模型的非线性和非参数概括。在这篇综述中，我们介绍了几种流行的深度学习模型，包括卷积神经网络、生成对抗网络、循环神经网络和自动编码器，及其在图像数据、序列数据和推荐系统中的应用。我们回顾了每个模型的架构，并强调了它们与传统统计模型的联系和差异。特别是，我们对最近关于独特的过度参数化现象的研究进行了简要概述，这解释了在深度学习中使用极大量参数的优点和优势。此外，我们还提供优化算法、超参数调整和计算资源方面的实用指导。
As one of the most rapidly developing artificial intelligence techniques, deep learning has been applied in various machine learning tasks and has received great attention in data science and statistics. Regardless of the complex model structure, deep neural networks can be viewed as a nonlinear and nonparametric generalization of existing statistical models. In this review, we introduce several popular deep learning models including convolutional neural networks, generative adversarial networks, recurrent neural networks, and autoencoders, with their applications in image data, sequential data and recommender systems. We review the architecture of each model and highlight their connections and differences compared with conventional statistical models. In particular, we provide a brief survey of the recent works on the unique overparameterization phenomenon, which explains the strengths and advantages of using an extremely large number of parameters in deep learning. In addition, we provide a practical guidance on optimization algorithms, hyperparameter tuning, and computing resources.