Boosting knowledge distillation and interpretability
Deep Neural Network (DNN) can be applied in many fields to predict classification and can obtain high accuracy. However, Deep Neural Network is a black box, which means that it’s hard to explain how the Deep Neural Network can derive specific classification directly. The generally accepted interpret...
Saved in:
主要作者: | Song, Huan |
---|---|
其他作者: | Ponnuthurai Nagaratnam Suganthan |
格式: | Thesis-Master by Coursework |
語言: | English |
出版: |
Nanyang Technological University
2021
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/150315 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
Principled asymmetric boosting approaches to rapid training and classification in face detection
由: Pham, Minh Tri
出版: (2009) -
Interpreting models for video action recognition
由: Daniel Wijaya
出版: (2021) -
Complex pattern recognition and evaluation : a knowledge-based approach to computer chess
由: Ravindra Lal Weeraratne Koggalage
出版: (2008) -
Speaker recognition system
由: Song, Liyan.
出版: (2012) -
Hand gesture recognition using RF-sensing
由: Tan, Sheng Rong
出版: (2021)