Skip to content

Basic code outline for population-based optimisation methods for training RNNs

Notifications You must be signed in to change notification settings

sjblim/population-based-rnn-optimisation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Population-based Global Optimisation Methods for RNNs

** WORK IN PROGRESS **

Include a basic Evolution Strategies and Particle Swarm Optimisation as an alternative to gradient based methods.

Key Reference:

Population-based Global Optimisation Methods for Learning Long-term Dependencies with RNNs. Bryan Lim, Stefan Zohren, and Stephen Roberts. 2019 ICML Time Series Workshop.

About

Basic code outline for population-based optimisation methods for training RNNs

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages