Jaime Rubio Hervas

Jaime Rubio Hervas

Auto-generated profile, based on publicly available information

Jaime Rubio Hervas

School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2015 in Aerospace Science and Technology
Verified
Journal Article
Closed access
JRJaime Rubio-Hervas
Jaime Rubio-Hervas
Dan ZhaoDan Zhao
Dan Zhao
MRMahmut Reyhanoglu
Mahmut Reyhanoglu

1 April 2016 in Communications in Nonlinear Science and Numerical Simulation
Verified
Journal Article
Closed access
JHJaime Rubio Hervas
Jaime Rubio Hervas
Mahmut ReyhanogluMahmut Reyhanoglu
Mahmut Reyhanoglu
Hui TangHui Tang
Hui Tang
EKErdal Kayacan
Erdal Kayacan

8 June 2018 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
WGWeili Guo
Weili Guo
YOYew-Soon Ong
Yew-Soon Ong
YZYingjiang Zhou
Yingjiang Zhou
JHJaime Rubio Hervas
Jaime Rubio Hervas
ASAiguo Song
Aiguo Song
HWHaikun Wei
Haikun Wei
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 information matrix (FIM) degenerates, the FIM plays a key role in the study of the singular learning dynamics of the MLPs. In this paper, we obtain the analytical form of the FIM for unipolar activation function-based MLPs where the input subjects to the Gaussian distribution with general covariance matrix and the unipolar error function is chosen as the activation function. Then three simulation experiments are taken to verify the validity of the obtained results.