Semi-supervised Learning Using Generative Adversarial Networks

Chuan Yu Chang, Tzu Yang Chen, Pau Choo Chung

研究成果: Conference contribution

14 引文 斯高帕斯(Scopus)

摘要

Machine learning is a powerful tool in many applications, but the most difficult process in machine learning is the collection of data and the labeling of data. Unsupervised and semi-supervised learning has thus become an important issue. In this paper, we introduce a semi-supervised learning approach which using generative adversarial networks to generate training samples. Those imitated samples were involved in training set to train the classifier, this can improve the stability and robustness of the classifier models. To demonstrate the performance of the proposed framework, four benchmarks including Iris, MNIST, CIFAR-10, and SVHN datasets were evaluated. The experimental results show that even in a small amount of training data, the proposed framework can predict more accurately than the existing methods.

原文English
主出版物標題Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018
編輯Suresh Sundaram
發行者Institute of Electrical and Electronics Engineers Inc.
頁面892-896
頁數5
ISBN(電子)9781538692769
DOIs
出版狀態Published - 2018 7月 2
事件8th IEEE Symposium Series on Computational Intelligence, SSCI 2018 - Bangalore, India
持續時間: 2018 11月 182018 11月 21

出版系列

名字Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

Conference

Conference8th IEEE Symposium Series on Computational Intelligence, SSCI 2018
國家/地區India
城市Bangalore
期間18-11-1818-11-21

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 理論電腦科學

指紋

深入研究「Semi-supervised Learning Using Generative Adversarial Networks」主題。共同形成了獨特的指紋。

引用此