雙向遞迴網絡
閱讀設定
雙向遞迴網絡(bidirectional recurrent network,BRN)係一種進階嘅遞迴神經網絡。雙向遞迴網絡嘅特徵係有兩個彼此之間唔相連嘅隱藏層,分別叫向前狀態(forward states;)同向後狀態(backward states;)。一個雙向遞迴網絡每次會讀取 個輸入,foreach , [1][2]:
最先嗰個時間點嘅 以及最後嗰個時間點嘅 可以會當做一啲事先設定好嘅常數。一個雙向遞迴網絡(右)嘅結構圖解如下[1]:
一個雙向遞迴網絡嘅輸出層會由過去同未來嗰度攞訊息-例如想像一個做機械翻譯嘅遞迴神經網絡,佢會攞一連串嘅英文字母做輸入,然後輸出就係一段相應嘅粵文字。喺每個時間點 ,佢會攞 10 個字,然後 foreach 字,佢會有一個輸出,個輸出會取決於打前嘅字同打後嘅字。雙向遞迴網絡最大嘅特徵係能夠埋考慮「未來」嘅訊息,而因為未來嘅訊息好多時都對做預測有用(尤其係喺語言處理上),所以雙向遞迴網絡能夠做到一啲普通嘅遞迴神經網絡做唔到嘅預測[1][3]。
睇埋
[編輯]攷
[編輯]- ↑ 1.0 1.1 1.2 Schuster, Mike, and Kuldip K. Paliwal. "Bidirectional recurrent neural networks." Signal Processing, IEEE Transactions on 45.11 (1997): 2673-2681.2. Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan
- ↑ Understanding Bidirectional RNN in PyTorch. Towards Data Science.
- ↑ T. Robinson, M. Hochberg, and S. Renals, "The use of recurrent neural networks in continuous speech recognition," in Automatic Speech Recognition: Advanced Topics, C. H. Lee, F. K. Soong, and K. K. Paliwal, Eds. Boston, MA: Kluwer, 1996, pp. 233–258.