Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/berenslab/fslm_repo

reproduce results of fslm paper

https://github.com/berenslab/fslm_repo

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.3%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

reproduce results of fslm paper

Basic Info
  • Host: GitHub
  • Owner: berenslab
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 5.75 MB
Statistics
  • Stars: 0
  • Watchers: 3
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 4 years ago · Last pushed over 3 years ago

https://github.com/berenslab/fslm_repo/blob/main/ 

# Efficient identification of informative features in simulation-based inference
This repository contains the code for reproducing results of the FSML paper [openreview.net/forum?id=AYQI3rlp9tW](https://openreview.net/forum?id=AYQI3rlp9tW). An updated and refactored version of the code can be found [here](https://github.com/berenslab/fslm).

## Installation
The necessary packages can be installed via:
`pip install .`

## Usage
The repository is structured as follows:
```
|-README.md
|-setup.py
|-notebooks
|-results
|-experiments
|  |-templates
|	    |-simulate.py
|	    |-full_experiment.py
|	    |-experiment_presimulated.py
|	|-run_experiments.sh
|	|-experiment2.py
|	|-experiment3.py
|	|-experiment4.py
|	|-(...)
|-sbi_feature_importance
	|-__init__.py
	|-snle.py
	|-utils.py
	|-metrics.py
	|-experiment_helper.py
	|-analysis.py
	|-toymodels.py
	|-snpe.py
|-ephys_helper
	|-__init__.py
	|-utils.py
	|-hh_simulator.py
	|-extractor.py
	|-features.py
	|-analysis.py
```

You can find the results to our experiments [here](https://zenodo.org/record/7104245) and reproduce the figures with the provided notebooks.

The templates provide an orientation for setting up FSLM experiments with HH models.

All experiments can be run via the provided bash_script (Only feasable with larger amounts of compute)
`bash run_experiments.sh`

Owner

  • Name: Berens Lab @ University of Tübingen
  • Login: berenslab
  • Kind: organization
  • Email: philipp.berens@uni-tuebingen.de
  • Location: Tübingen, Germany

Department of Data Science at the Hertie Institute for AI in Brain Health, University of Tübingen

GitHub Events

Total
Last Year

Dependencies

setup.py pypi
  • brian2 *
  • joblib *
  • matplotlib *
  • numpy *
  • pandas *
  • sbi *
  • scipy *
  • seaborn *
  • six *
  • torch *
  • tqdm *