This repository contains code to perform experiments with recurrent predictive coding networks on associative memory tasks.
The preprint associated with the code repository can be found here.
To run the code, you should first install Anaconda or Miniconda (preferably the latter), and then clone this repository to your local machine.
Once these are installed and cloned, you can simply use the appropriate .yml file to create a conda environment.
For Ubuntu or Mac OS, open a terminal, go to the repository directory; for Windows, open the Anaconda Prompt, and then enter:
conda env create -f environment.ymlconda activate cov-envpip install -e .
Once the above are done, you can simply run a script by entering for example:
python scripts/single_layer_PCNs.py
A directory named results will the be created to store all the data and figures collected from the experiments.
A jupyter notebook will be produced to show how to generate figure from our paper based on the collected results (Coming Soon).