Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | MLSP-L3.1 |
| Session: | Learning Theory and Modeling |
| Time: | Friday, May 21, 15:30 - 15:50 |
| Presentation: |
Lecture |
| Topic: |
Machine Learning for Signal Processing: Learning Theory and Modeling |
| Title: |
THEORY OF MONTE CARLO SAMPLING-BASED ALOPEX ALGORITHMS FOR NEURAL NETWORKS |
| Authors: |
Zhe Chen; McMaster University | | |
| | Simon Haykin; McMaster University | | |
| | Suzanna Becker; McMaster University | | |
| Abstract: |
We propose two novel Monte Carlo sampling-based Alopex algorithmsfor training neural networks. The proposed algorithms naturallycombine the sequential Monte Carlo estimation and Alopex-likeprocedure for gradient-free optimization, and the learningproceeds within the recursive Bayesian estimation framework.Experimental results on various problems show encouragingconvergence results. |
| |
| Back | |