Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/alfa-group/lipizzaner-ae

Cooperative Spatial Topologies for Autoencoder Training

https://github.com/alfa-group/lipizzaner-ae

Science Score: 13.0%

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

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.1%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Cooperative Spatial Topologies for Autoencoder Training

Basic Info
  • Host: GitHub
  • Owner: ALFA-group
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 29.3 KB
Statistics
  • Stars: 0
  • Watchers: 3
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License

README.md

Lipizzaner Autoencoder (Lipi-Ae)

Installation

Create virtual environment. E.g python3 -m venv ~/.venvs/lipi_ae_gecco_24

Activate virtual environment. E.g source ~/.venvs/lipi_ae_gecco_24/bin/activate

Install dependencies pip install -r requirements.txt

Quick start

Binary Clustering

Create Binary Clustering problems PYTHONPATH=src python src/aes_lipi/datasets/data_loader.py --n_dim 1000 --n_clusters 10

Test binary clustering problem and autoencoder PYTHONPATH=src python src/aes_lipi/environments/binary_clustering.py --method=Autoencoder --dataset_name=binary_clustering_10_100_1000

Run Lipi-Ae on binary clustering problem PYTHONPATH=src python src/aes_lipi/lipi_ae.py --configuration_file=tests/gecco_2024/configurations/binary_clustering/test_bc/binary_clustering_epoch_node_demo_lipi_ae.json

Experiment

Run experiments time PYTHONPATH=src python src/aes_lipi/utilities/gecco_experiments.py --configuration_directory tests/gecco_2024/configurations/binary_clustering/test_bc --sensitivity tests/gecco_2024/configurations/binary_clustering/test_bc/sensitivity_values.json

Update dataset in sensitivity_values.json key "dataset_name" by adding the new dataset to the list

Analyze data from --root_dir based on --param_dir parameters. time PYTHONPATH=src python src/aes_lipi/utilities/analyse_data.py --root_dir out_binary_clustering --param_dir out_binary_clustering

Compare ANN parameters

Save the parameters at every iteration Run Lipi-Ae with solution concept best_case PYTHONPATH=src python src/aes_lipi/lipi_ae.py --dataset_name binary_clustering_10_100_1000 --environment AutoencoderBinaryClustering --epochs 3 --batch_size 400 --population_size 2 --ae_quality_measures L1 --solution_concept best_case --checkpoint_interval 1 --do_not_overwrite_checkpoint

Reference

```

@inproceedings{hemberg2024ae, title={Cooperative Spatial Topologies for Autoencoder Training}, author={Hemberg, Erik and Toutouh, Jamal and O'Reilly, Una-May}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference}, year={2024} } ```

Owner

  • Name: Anyscale Learning For All (ALFA)
  • Login: ALFA-group
  • Kind: organization
  • Email: alfa-apply@csail.mit.edu
  • Location: Cambridge, MA, USA

Scalable machine learning technology, Adversarial AI, Evolutionary algorithms, and data science frameworks.

GitHub Events

Total
Last Year

Dependencies

pyproject.toml pypi
requirements.txt pypi
  • matplotlib *
  • numpy *
  • pandas *
  • piq *
  • requests *
  • seaborn *
  • torch *
  • torchmetrics *
  • torchvision *