Skip to main content

No project description provided

Project description

Official pytorch library for Tversky Neural Networks

tversky requires PyTorch ≥ 2.0. Install it first following the instructions at https://pytorch.org/get-started, then pip install tversky.

TODO

  • cleanup dependencies
  • tests
  • pipy publishing workflow
  • readme
  • link in research repository

License

LICENSE.txt

Citation

If you use this work, please cite the following paper:

@inproceedings{doumbouya2026tversky,
    title={Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity},
    author={Moussa Koulako Bala Doumbouya and Dan Jurafsky and Christopher D Manning},
    booktitle={The Fourteenth International Conference on Learning Representations},
    year={2026},
    url={https://openreview.net/forum?id=koKWoKaMrE}
}

Project details


Download files

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

Source Distribution

tversky-0.1.0.tar.gz (231.2 kB view details)

Uploaded Source

Built Distribution

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

tversky-0.1.0-py3-none-any.whl (42.2 kB view details)

Uploaded Python 3

File details

Details for the file tversky-0.1.0.tar.gz.

File metadata

  • Download URL: tversky-0.1.0.tar.gz
  • Upload date:
  • Size: 231.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tversky-0.1.0.tar.gz
Algorithm Hash digest
SHA256 864f92b9c550a2ae9e151f933ed2a99e69a2eef1b5b807558fe98f1f77f8c0eb
MD5 70d5719b719c0880fc887e24abe6d633
BLAKE2b-256 eb67a921b2401ef3bbe5e80c35eab5d0e6b8025ce3b98df0c07ad073d670ca51

See more details on using hashes here.

Provenance

The following attestation bundles were made for tversky-0.1.0.tar.gz:

Publisher: pypi.yml on mdoumbouya/tversky

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file tversky-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: tversky-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 42.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tversky-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 85bca8c1224742bbef5c754e13ffe65881b332d6d1b223fdf926a45b5bf5adcc
MD5 1bc5637f239df9beb1db2cb5801a6238
BLAKE2b-256 7986abb7703d80bcf55ddc7a6f1bb0deda8e16e554e0cb23d45189efe7a17a87

See more details on using hashes here.

Provenance

The following attestation bundles were made for tversky-0.1.0-py3-none-any.whl:

Publisher: pypi.yml on mdoumbouya/tversky

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

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