Improved Computation for Levenberg–Marquardt Training
By Bogdan M. Wilamowski, Hao Yu. IEEE Transactions on Neural Networks, 2010
591 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computational Theory and Mathematics, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/d77464e83792942ec86689f2fec21edaba8d9f31
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- David K. Hunter
- Michael S. Pukish III
- Janusz Kolbusz
- Hao Yu
- Bogdan M. Wilamowski
- Stanislaw Paszczynski
- Tiantian Xie
- Zhengjun Zha
In Computational Theory and Mathematics
In Statistical and Nonlinear Physics
Citations in the corpus
- FPGAs in Industrial Control Applications (2011, unknown): “Many recent publications ([9], [99], [100], [101]) consider the FPGA as an effective implementation solution of control algorithms for industrial applications.”
- Advantages of Radial Basis Function Networks for Dynamic System Design (2011, methodology): “By incorporating the second-order computation procedure presented in [47], the update rule of the ISO algorithm is”
- Selection of Proper Neural Network Sizes and Architectures—A Comparative Study (2012, methodology): “This advantage allows the NBN algorithm to be used for problems with essentially an unlimited number of patterns [46].”
- Image De-raining via Continual Learning (2021, methodology): “Motivated by GaussNewton method [38], when conventional loss is SSE (Sum”