- Hands-On Meta Learning with Python
- Sudharsan Ravichandiran
- 96字
- 2021-07-02 14:29:16
Learning the metric space
In the metric-based meta learning setting, we will learn the appropriate metric space. Let's say we want to learn the similarity between two images. In the metric-based setting, we use a simple neural network that extracts the features from two images and finds the similarity by computing the distance between features of these two images. This approach is widely used in a few-shot learning setting where we don't have many data points. In the upcoming chapters, we will learn about metric-based learning algorithms such as Siamese networks, prototypical networks, and relation networks.
推薦閱讀
- Microsoft SQL Server企業級平臺管理實踐
- 智能數據時代:企業大數據戰略與實戰
- 數據庫設計與應用(SQL Server 2014)(第二版)
- 高維數據分析預處理技術
- INSTANT Android Fragmentation Management How-to
- 二進制分析實戰
- 計算機視覺
- Filecoin原理與實現
- 企業大數據處理:Spark、Druid、Flume與Kafka應用實踐
- Learning Ansible
- 數據庫技術與應用:SQL Server 2008
- 一本書講透數據治理:戰略、方法、工具與實踐
- 一本書讀懂區塊鏈(第2版)
- Applying Math with Python
- 反饋:化解不確定性的數字認知論