Skip to content

About

Training tasks with long temporal dependencies

Resources

Stars

0 stars

Watchers

1 watching

Forks

Latest commit

 

History

5 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

multi-trial-tasks

Training tasks with long temporal dependencies

Work done in collaboration with Wayne Soo

Applies annealed skip-connections through time to support training of biological RNNs on tasks with long (across trial) temporal dependencies.

Currently implemented Reversal Learning and classic WCST (set task variable in main_workspace.py)

To run, call main_workspace.py with command line arguments where is the number of time steps to skip over

About

Training tasks with long temporal dependencies

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages