Recent advances in convolutional neural networks
Recent advances in convolutional neural networks
复制标题
卷积神经网络的最新进展
DOI：
10.1016/j.patcog.2017.10.013
复制
发表时间：
2018-05-01
影响因子：
8
通讯作者：
Chen, Tsuhan
中科院分区：
文献类型：
--
作者：
Gu, Jiuxiang;Wang, Zhenhua;Chen, Tsuhan
在过去的几年里，深度学习在视觉识别、语音识别和自然语言处理等各种问题上都取得了很好的表现。在不同类型的深度神经网络中，卷积神经网络得到了最广泛的研究。利用标注数据量的快速增长和图形处理器单元能力的极大提高，卷积神经网络的研究迅速兴起，并在各种任务上取得了最先进的结果。本文对卷积神经网络的最新研究进展进行了综述。详细介绍了CNN在层设计、激活函数、损失函数、正则化、优化和快速计算等方面的改进。此外，我们还介绍了卷积神经网络在计算机视觉、语音和自然语言处理中的各种应用。(C)2017爱思唯尔有限公司。保留所有权利。
In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing. Among different types of deep neural networks, convolutional neural networks have been most extensively studied. Leveraging on the rapid growth in the amount of the annotated data and the great improvements in the strengths of graphics processor units, the research on convolutional neural networks has been emerged swiftly and achieved state-of-the-art results on various tasks. In this paper, we provide a broad survey of the recent advances in convolutional neural networks. We detailize the improvements of CNN on different aspects, including layer design, activation function, loss function, regularization, optimization and fast computation. Besides, we also introduce various applications of convolutional neural networks in computer vision, speech and natural language processing. (C) 2017 Elsevier Ltd. All rights reserved.