专栏名称: 机器学习研究会
机器学习研究会是北京大学大数据与机器学习创新中心旗下的学生组织,旨在构建一个机器学习从事者交流的平台。除了及时分享领域资讯外,协会还会举办各种业界巨头/学术神牛讲座、学术大牛沙龙分享会、real data 创新竞赛等活动。
目录
相关文章推荐
爱可可-爱生活  ·  【ComfyUI-Lotus:为Lotus深 ... ·  2 天前  
爱可可-爱生活  ·  几篇论文实现代码:《DiffGS: ... ·  2 天前  
人工智能那点事  ·  坠崖一年多的无人机突然回来了?网友:记得给这 ... ·  3 天前  
爱可可-爱生活  ·  几篇论文实现代码:《Is One GPU ... ·  5 天前  
51好读  ›  专栏  ›  机器学习研究会

【推荐】深度卷积神经网络图像分类综述

机器学习研究会  · 公众号  · AI  · 2017-06-14 20:52

正文



点击上方“机器学习研究会”可以订阅哦
摘要
 

转自:爱可可-爱生活

Convolutional neural networks (CNNs) have been applied to visual tasks since the late 1980s. However, despite a few scattered applications, they were dormant until the mid-2000s when developments in computing power and the advent of large amounts of labeled data, supplemented by improved algorithms, contributed to their advancement and brought them to the forefront of a neural network renaissance that has seen rapid progression since 2012. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art deep learning systems. Along the way, we analyze (1) their early successes, (2) their role in the deep learning renaissance, (3) selected symbolic works that have contributed to their recent 


链接:

http://www.mitpressjournals.org/doi/abs/10.1162/NECO_a_00990


下载链接:

https://pan.baidu.com/s/1jHYC4AU


原文链接:

https://m.weibo.cn/1402400261/4118422025152727

“完整内容”请点击【阅读原文】
↓↓↓