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 |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/139916 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
A novel multi-objective optimization based experimental design and its application for physiological model of type 1 diabetes
by: Maheshwari, V., et al.
Published: (2014) -
Accelerating computations in two-stage Bayesian system identification with Fisher information matrix and eigenvalue sensitivity
by: Zhu, Jia-Xin, et al.
Published: (2022) -
Marginalising posterior covariance matrix with application to Bayesian operational modal analysis
by: Au, Siu-Kui
Published: (2024) -
Fisher information as general metrics of quantum synchronization
by: Shen, Yuan, et al.
Published: (2023) -
EFFECTIVE BOUNDARY CONDITIONS FOR THE FISHER-KPP EQUATIONS
by: GENG XINGRI
Published: (2024)