Pseudo-Label：The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks
這是一篇發表在 ICML 2013 的文章，作爲半監督神經網絡的一篇代表文章。【文章】【代碼】文章中採用了pesudo-label的方法來作爲無標籤樣本的僞標籤。文章的主要想法是self-training，僞標籤的確定也是通過有標記樣本訓練的神經網絡，來對無標記的樣本進行預測，選擇出只選擇對每個未標記的樣本具有最大預測概率的類。 這個方法爲什麼會成功，文章中解釋到：（1）低密度分離（2）熵要小，這
相關文章
- 1. Neural Networks and Deep Learning
- 2. Neural Networks and Deep Learning -- Class 4: Deep Neural Networks
- 3. Neural Networks and Deep Learning -- Class 3: Shallow neural networks
- 4. COURSE 1 Neural Networks and Deep Learning
- 5. Neural Networks and Deep Learning-引論
- 6. neural networks and deep learning-chapter1-2
- 7. neural networks and deep learning-chapter1-3
- 8. Neural Networks and Deep Learning -- Class 2: Neural Network Basics
- 9. 論文筆記系列-Simple And Efficient Architecture Search For Neural Networks
- 10. Neural Networks and Deep Learning（week4）深層神經網絡（Deep Neural Networks）
- 更多相關文章...
- • Swift for 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • RxJava操作符（七）Conditional and Boolean
- • Java Agent入門實戰（三）-JVM Attach原理與使用
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Neural Networks and Deep Learning
- 2. Neural Networks and Deep Learning -- Class 4: Deep Neural Networks
- 3. Neural Networks and Deep Learning -- Class 3: Shallow neural networks
- 4. COURSE 1 Neural Networks and Deep Learning
- 5. Neural Networks and Deep Learning-引論
- 6. neural networks and deep learning-chapter1-2
- 7. neural networks and deep learning-chapter1-3
- 8. Neural Networks and Deep Learning -- Class 2: Neural Network Basics
- 9. 論文筆記系列-Simple And Efficient Architecture Search For Neural Networks
- 10. Neural Networks and Deep Learning（week4）深層神經網絡（Deep Neural Networks）