论文阅读笔记《TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning》
核心思想 本文提出一种基于度量学习的小样本学习算法（TapNet），其特点是设计了一个与任务相关的分类空间，在该空间内进行距离度量，而且每个类别的参考向量 Φ \Phi Φ是通过学习更新得到的，而不是根据训练样本的特征向量计算得到的，这与PN和MN算法有明显的不同。整个算法的处理过程如下图所示。 与所有的采用Episode训练方式的算法一样，训练集包含支持集 { ( x 1 , y 1 )
相关文章
- 1. 论文阅读笔记《Meta-Learning with Memory-Augmented Neural Networks》
- 2. 论文《Learning both Weights and Connections for Efficient Neural Network》阅读笔记
- 3. 论文阅读笔记《Edge-Labeling Graph Neural Network for Few-shot Learning》
- 4. Document Modeling with Gated Recurrent Neural Network for Sentiment Classification 论文阅读笔记
- 5. 【论文阅读笔记】Document Modeling with Gated Recurrent Neural Network for Sentiment Classification
- 6. Machine Learning & Deep Learning 论文阅读笔记
- 7. M4C:Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA ---论文阅读笔记
- 8. 论文阅读笔记《Few-Shot Learning with Graph Neural Networks》
- 9. 论文阅读笔记《Meta-Learning of Neural Architectures for Few-Shot Learning》
- 10. Deep Residual Learning for Image Recognition--ResNet论文阅读笔记
- 更多相关文章...
- • RSS 阅读器 - RSS 教程
- • PHP 实例 - AJAX RSS 阅读器 - PHP教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • JDK13 GA发布：5大特性解读
相关标签/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。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文阅读笔记《Meta-Learning with Memory-Augmented Neural Networks》
- 2. 论文《Learning both Weights and Connections for Efficient Neural Network》阅读笔记
- 3. 论文阅读笔记《Edge-Labeling Graph Neural Network for Few-shot Learning》
- 4. Document Modeling with Gated Recurrent Neural Network for Sentiment Classification 论文阅读笔记
- 5. 【论文阅读笔记】Document Modeling with Gated Recurrent Neural Network for Sentiment Classification
- 6. Machine Learning & Deep Learning 论文阅读笔记
- 7. M4C:Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA ---论文阅读笔记
- 8. 论文阅读笔记《Few-Shot Learning with Graph Neural Networks》
- 9. 论文阅读笔记《Meta-Learning of Neural Architectures for Few-Shot Learning》
- 10. Deep Residual Learning for Image Recognition--ResNet论文阅读笔记