Fisher information matrix of unipolar activation function-based multilayer perceptrons
The multilayer perceptrons (MLPs) are widely used in many fields, however, singularities in the parameter space may seriously influence the learning dynamics of MLPs and cause strange learning behaviors. Given that the singularities are the subspaces of the parameter space where the Fisher informati...
Saved in:
Main Authors: | Guo, Weili, Ong, Yew-Soon, Zhou, Yingjiang, Hervas, Jaime Rubio, Song, Aiguo, Wei, Haikun |
---|---|
其他作者: | School of Computer Science and Engineering |
格式: | Article |
語言: | English |
出版: |
2020
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/139916 |
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
-
A novel multi-objective optimization based experimental design and its application for physiological model of type 1 diabetes
由: Maheshwari, V., et al.
出版: (2014) -
Accelerating computations in two-stage Bayesian system identification with Fisher information matrix and eigenvalue sensitivity
由: Zhu, Jia-Xin, et al.
出版: (2022) -
Marginalising posterior covariance matrix with application to Bayesian operational modal analysis
由: Au, Siu-Kui
出版: (2024) -
Fisher information as general metrics of quantum synchronization
由: Shen, Yuan, et al.
出版: (2023) -
EFFECTIVE BOUNDARY CONDITIONS FOR THE FISHER-KPP EQUATIONS
由: GENG XINGRI
出版: (2024)