Skip to main content

neat (wip)

Explorations into NEAT and some of its derivative research

install

In project root, run

$ sh install.sh

quick test

$ uv run train_lunar.py

citations

@article{Stanley2011CompetitiveCT,
    title   = {Competitive Coevolution through Evolutionary Complexification},
    author  = {Kenneth O. Stanley and Risto Miikkulainen},
    journal = {ArXiv},
    year    = {2011},
    volume  = {abs/1107.0037},
    url     = {https://api.semanticscholar.org/CorpusID:11881625}
}
@inproceedings{4665912,
    author  = {Miguel, Cesar Gomes and Silva, Carolina Feher da and Netto, Marcio Lobo},
    booktitle = {2008 10th Brazilian Symposium on Neural Networks},
    title   = {Structural and Parametric Evolution of Continuous-Time Recurrent Neural Networks},
    year    = {2008},
    doi     = {10.1109/SBRN.2008.12}
}
@article{Khamesian2021HybridSN,
    title   = {Hybrid self-attention NEAT: a novel evolutionary self-attention approach to improve the NEAT algorithm in high dimensional inputs},
    author  = {Saman Khamesian and Hamed Malek},
    journal = {Evolving Systems},
    year    = {2021},
    pages   = {1-15},
    url     = {https://api.semanticscholar.org/CorpusID:244920723}
}
@article{Hornby2006AutomatedAD,
    title   = {Automated Antenna Design with Evolutionary Algorithms},
    author  = {Gregory Hornby and Al Globus and Derek S. Linden and Jason D. Lohn},
    journal = {Space},
    year    = {2006},
    url     = {https://api.semanticscholar.org/CorpusID:8290212}
}
@inproceedings{schrum:gecco14,
    title   = {Evolving Multimodal Behavior With Modular Neural Networks in Ms. Pac-Man},
    author  = {Jacob Schrum and Risto Miikkulainen},
    booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014)},
    month   = {July},
    address = {Vancouver, BC, Canada},
    pages   = {325--332},
    note    = {Best Paper: Digital Entertainment and Arts},
    url     = {http://www.cs.utexas.edu/users/ai-lab?schrum:gecco2014},
    year    = {2014}
@article{stanley:ec02,
    title   = {Evolving Neural Networks Through Augmenting Topologies},
    author  = {Kenneth O. Stanley and Risto Miikkulainen},
    volume  = {10},
    journal = {Evolutionary Computation},
    number  = {2},
    pages   = {99-127},
    url     = "http://nn.cs.utexas.edu/?stanley:ec02",
    year    = {2002}
}
@misc{doerr2017fastgeneticalgorithms,
    title   = {Fast Genetic Algorithms},
    author  = {Benjamin Doerr and Huu Phuoc Le and Régis Makhmara and Ta Duy Nguyen},
    year    = {2017},
    eprint  = {1703.03334},
    archivePrefix = {arXiv},
    primaryClass = {cs.NE},
    url     = {https://arxiv.org/abs/1703.03334},
}
@misc{legg2004tournamentversusfitnessuniform,
    title   = {Tournament versus Fitness Uniform Selection},
    author  = {Shane Legg and Marcus Hutter and Akshat Kumar},
    year    = {2004},
    eprint  = {cs/0403038},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG},
    url     = {https://arxiv.org/abs/cs/0403038},
}
@article{hiraga2024improving,
    title   = {Improving the performance of mutation-based evolving artificial neural networks with self-adaptive mutations},
    author  = {Hiraga, Motoaki and Komura, Masahiro and Miyamoto, Akiharu and Morimoto, Daichi and Ohkura, Kazuhiro},
    journal = {PLOS ONE},
    volume  = {19},
    number  = {7},
    pages   = {e0307084},
    year    = {2024},
    publisher = {Public Library of Science},
    doi     = {10.1371/journal.pone.0307084},
    url     ={https://doi.org/10.1371/journal.pone.0307084}
}

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

x_neat-0.0.3.tar.gz (22.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

x_neat-0.0.3-py3-none-any.whl (18.7 kB view details)

Uploaded Python 3

File details

Details for the file x_neat-0.0.3.tar.gz.

File metadata

  • Download URL: x_neat-0.0.3.tar.gz
  • Upload date:
  • Size: 22.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.17

File hashes

Hashes for x_neat-0.0.3.tar.gz
Algorithm Hash digest
SHA256 3b9715b8116677baba92cb76ae4c7247d3d449ea79685c681f5b50a6dc5cb297
MD5 6efa6186b2c8fdb47d8647b818508a9c
BLAKE2b-256 c5381ab67a30fe9451ee9492be068c3f374287b000e33ae7752ca99b8eec9844

See more details on using hashes here.

File details

Details for the file x_neat-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: x_neat-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 18.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.17

File hashes

Hashes for x_neat-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 f964edde19682b4a556d3f2246882577d295171f7e98d27fa8eda59fc9c78731
MD5 d229ef1c281793d4e92b638d4f0fec2a
BLAKE2b-256 3cc6fae9d6952c33b6feb25576f367701ad2deb6d4f361f32908923c8b4e2ca3

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page