Multi-target deep neural networks: Theoretical analysis and implementation
In this work, we propose a novel deep neural network referred to as Multi-Target Deep Neural Network (MT-DNN). We theoretically prove that different stable target models with shared learning paths are stable and can achieve optimal solutions respectively. Based on GoogleNet, we design a single model...
Saved in:
Main Authors: | ZENG, Zeng, LIANG, Nanying, YANG, Xulei, HOI, Steven C. H. |
---|---|
格式: | text |
語言: | English |
出版: |
Institutional Knowledge at Singapore Management University
2018
|
主題: | |
在線閱讀: | https://ink.library.smu.edu.sg/sis_research/4187 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Singapore Management University |
語言: | English |
相似書籍
-
Multi-target deep neural networks: Theoretical analysis and implementation
由: ZENG, Zeng, et al.
出版: (2018) -
Recent advances in deep learning for object detection
由: WU, Xiongwei, et al.
出版: (2020) -
Deep anomaly detection with deviation networks
由: PANG, Guansong, et al.
出版: (2019) -
Audee: Automated testing for deep learning frameworks
由: GUO, Qianyu, et al.
出版: (2020) -
Keras R-CNN: Library for cell detection in biological images using deep neural networks
由: Hung, J., et al.
出版: (2021)