A-SDLM: an asynchronous Stochastic Learning Algorithm for fast distributed learning
We propose an asynchronous version of stochastic secondorder optimization algorithm for parallel distributed learning. Our proposed algorithm, namely Asynchronous Stochastic Diagonal Levenberg-Marquardt (A-SDLM) contains only a single hyper-parameter (i.e. the learning rate) while still retaining it...
Saved in:
Main Authors: | Hani, M. K., Liew, S. S. |
---|---|
Format: | Conference or Workshop Item |
Published: |
2015
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/59161/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Distributed B-SDLM: accelerating the training convergence of deep neural networks through parallelism
by: Liew, S. S., et al.
Published: (2016) -
An optimized second order stochastic learning algorithm for neural network training
by: Liew, S. S., et al.
Published: (2016) -
An Asynchronous Distributed Dynamic Channel Assignment Scheme for Dense WLANs
by: Drieberg , Micheal, et al.
Published: (2008) -
Advances in Particle Swarm Algorithms in Asynchronous, Discrete and Multi-Objective Optimization
by: Zuwairie, Ibrahim
Published: (2014) -
Fast and efficient sequential learning algorithms using direct-link RBF networks
by: Asirvadam , Vijanth Sagayan, et al.
Published: (2003)