Skip to content

Official implementation of "Traveling Waves Encode the Recent Past and Enhance Sequence Learning" (ICLR 2024)

License

Notifications You must be signed in to change notification settings

HOIAN17/Wave_RNNs

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Traveling Waves Encode the Recent Past
and Enhance Sequence Learning

This repository contains the implementation to reproduce the experiments of the ICLR 2024 submission: "Traveling Waves Encode the Recent Past
and Enhance Sequence Learning".

To install the requirements: conda env create -f environment.yml

This repo is equipped with Weights & Biases tracking by default. To enable it you must first install wandb separately: pip install wandb

Then, enter your Project Name, Entitiy Name, and Logging directory into the initalization of each task file: wandb.init(name=args.run_name, project='PROJECT_NAME', entity='ENTITY_NAME', dir='WANDB_DIR', config=args)

For more information on making a Weight & Biases account see (creating a weights and biases account) and the associated quickstart guide.

About

Official implementation of "Traveling Waves Encode the Recent Past and Enhance Sequence Learning" (ICLR 2024)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%