Self-supervised predictive learning accounts for cortical layer-specificity

https://www.nature.com/articles/s41467-025-61399-5 (Nature Comms 2025)

This repository contains the code to run the experiments for the paper: Self-supervised predictive learning accounts for cortical layer-specificity.

Dependencies

To install the requrired packages, create a new conda environment using:

conda env create -f environment.yaml

Training the neo-ssl model

Command line

To train run the experiment, simply pass the figure number as an argument for the run.py. For example, to run the experiment for figure 2, execute the following command:

python run.py --exp fig2

Plot the results

For each experiment, there is a jupyter notebook in plotting folder that plots the results.