推荐 论文:基于卷积K均值聚类算法的CNN无监督学习

Posted 2021-04-08 机器学习研究会

点击上方 “公众号”可以订阅哦！

摘要

转自：爱可可-爱生活

The task of labeling data for training deep neural networks is daunting and tedious, requiring millions of labels to achieve the current state-of-the-art results. Such reliance on large amounts of labeled data can be relaxed by exploiting hierarchical features via unsupervised learning techniques. In this work, we propose to train a deep convolutional network based on an enhanced version of the k-means clustering algorithm, which reduces the number of correlated parameters in the form of similar filters, and thus increases test categorization accuracy. We call our algorithm convolutional k-means clustering. We further show that learning the connection between the layers of a deep convolutional neural network improves its ability to be trained on a smaller amount of labeled data. Our experiments show that the proposed algorithm outperforms other techniques that learn filters unsupervised. Specifically, we obtained a test accuracy of 74.1% on STL-10 and a test error of 1.4% on MNIST.

链接：

http://arxiv.org/abs/1511.06241

原文链接：

http://m.weibo.cn/1402400261/3911553864646037?sourcetype=page&lfid=2302592000382195&lcardid=2302592000382195_-_3911553864646037&mid=3911553864646037&luicode=10000011&_status_id=3911553864646037&uicode=10000002

欢迎参加人工智能与机器学习微信讲座！

参加方法：微信扫描以下二维码或搜索ML_admin，加群主为好友。

我们安排了群务处理您的申请请求。

“完整内容”请点击【阅读原文】

↓↓↓