Abstract
This article is to comment on the derivation of the weight-update stability of in-parameter-linear nonlinear learning system with the gradient descent learning rule in the above article. Our comments are not to disqualify the commented article's whole contribution; however, the issues should be pointed out to avoid their proliferation.
Original language | English |
---|---|
Journal | IEEE Transactions on Neural Networks and Learning Systems |
DOIs | |
Publication status | Accepted/In press - 2021 |
Externally published | Yes |
Keywords
- Convergence analysis
- Education
- Eigenvalues and eigenfunctions
- Europe
- gradient descent
- in-parameter-linear nonlinear learning system
- Investment
- Learning systems
- Mechanical engineering
- Stability criteria
- weight-update stability.
ASJC Scopus subject areas
- Software
- Computer Science Applications
- Computer Networks and Communications
- Artificial Intelligence