Stochastic diagonal approximate greatest descent in neural networks

Stochastic diagonal approximate greatest descent in neural networks

© 2017 IEEE. Optimization is important in neural networks to iteratively update weights for pattern classification. Existing optimization techniques suffer from suboptimal local minima and slow convergence rate. In this paper, stochastic diagonal Approximate Greatest Descent (SDAGD) algorithm is pro...

Full description

Bibliographic Details
Main Authors: Tan, H., Lim, Hann, Harno, H.
Format: Conference Paper
Published: 2017
Online Access:http://hdl.handle.net/20.500.11937/57712

Internet

http://hdl.handle.net/20.500.11937/57712

Similar Items