阿里few shot learning文章的個人理解
先貼結構圖： 1、每次C類，每類K樣本，剩下的是測試集。 2、encoder層是BiLSTM+attention，得到編碼向量，假設隱含層個數是96個，句子長度是30，暫不考慮batch_size，那麼每個字的隱含層就是1*192向量，整個H就是30*192，那麼attention的最後輸出就是一個1*192的向量（計算公式如下，權重矩陣W是30*192的矩陣）。
相關文章
- 1. Zero-shot Learning / One-shot Learning / Few-shot Learning
- 2. Zero-shot / One-shot / Few-shot Learning
- 3. Few-shot-learning
- 4. few-shot learning幾篇論文
- 5. 【論文理解】Shot in The Dark: Few-Shot Learning with No Base-Class Labels
- 6. few-shot learning總結
- 7. Zero-shot Learning / One-shot Learning / Few-shot Learning/傳統 Learning
- 8. few-shot learning, zero-shot learning, one-shot learning,any-shot learning, C-way K-shot，Meta-learn
- 9. 深度學習: Zero-shot Learning / One-shot Learning / Few-shot Learning
- 10. Few-shot Learning with Graph Neural Networks
- 更多相關文章...
- • PHP 文件處理 - PHP教程
- • UDP報文格式詳解 - TCP/IP教程
- • 使用阿里雲OSS+CDN部署前端頁面與加速靜態資源
- • 三篇文章瞭解 TiDB 技術內幕——說存儲
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. Zero-shot Learning / One-shot Learning / Few-shot Learning
- 2. Zero-shot / One-shot / Few-shot Learning
- 3. Few-shot-learning
- 4. few-shot learning幾篇論文
- 5. 【論文理解】Shot in The Dark: Few-Shot Learning with No Base-Class Labels
- 6. few-shot learning總結
- 7. Zero-shot Learning / One-shot Learning / Few-shot Learning/傳統 Learning
- 8. few-shot learning, zero-shot learning, one-shot learning,any-shot learning, C-way K-shot，Meta-learn
- 9. 深度學習: Zero-shot Learning / One-shot Learning / Few-shot Learning
- 10. Few-shot Learning with Graph Neural Networks