Skip to main content

Latent Space Geometry for Neural Networks in Python

Project description

nlgm banner


[!WARNING] This package is still in its early stages. Updates may cause breaking changes.

Neural Geometry is a Python library designed to explore and manipulate the geometric properties of neural network latent spaces. It provides a set of tools and methods to understand the complex, high-dimensional spaces that neural networks operate in, inspired by recent approaches (e.g. Borde et al., 2023).

The primary features of Neural Geometry include:

  • An implementation of the neural latent geometry search framework. This framework provides a unique approach to product manifold inference, which can be beneficial in various fields such as machine learning and data analysis.
  • A selection of optimization methods to cater to different needs and requirements. These methods can be used to fine-tune the performance of the neural latent geometry search framework.

This package is designed to be compatible with popular scientific computing libraries such as NumPy and PyTorch, making it a versatile tool for researchers and developers working in these environments. Comprehensive documentation is available at docs.

Installation

Neural Geometry requires Python 3.12 or newer.

To install Neural Geometry, use uv:

uv pip install neural-geometry

You can install optional packages for development or visualization using:

uv sync --extra dev --extra vis
uv pip install -e ".[dev,vis]"        # editable install from pyproject.toml
uv pip install neural-geometry[dev,vis]  # install from pypi

Usage

After installing, you can import the package and use it by following the example.

Contributing

Contributions to Neural Geometry are welcome! To contribute:

  1. Fork the repository.
  2. Install the pre-commit hooks using pre-commit install.
  3. Create a new branch for your changes.
  4. Make your changes in your branch.
  5. Submit a pull request.

Before submitting your pull request, please make sure your changes pass all tests.

uv run pytest

License

Neural Geometry is licensed under the MIT License. See the LICENSE file for more details.

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

neural_geometry-0.1.3.tar.gz (12.5 kB view details)

Uploaded Source

Built Distribution

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

neural_geometry-0.1.3-py3-none-any.whl (14.0 kB view details)

Uploaded Python 3

File details

Details for the file neural_geometry-0.1.3.tar.gz.

File metadata

  • Download URL: neural_geometry-0.1.3.tar.gz
  • Upload date:
  • Size: 12.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for neural_geometry-0.1.3.tar.gz
Algorithm Hash digest
SHA256 bacbdf2c904f43522a419eb1ed5f35cad19e62afbc71126cac4a745b7025d836
MD5 ef835319feca892bed8b6bc8b67e03b8
BLAKE2b-256 b37798dd787bdfeaa9669dc6470bfed02a2e96955c532fe6a86b025afacb5826

See more details on using hashes here.

Provenance

The following attestation bundles were made for neural_geometry-0.1.3.tar.gz:

Publisher: release.yaml on ae-bii/neural-geometry

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

File details

Details for the file neural_geometry-0.1.3-py3-none-any.whl.

File metadata

File hashes

Hashes for neural_geometry-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 855792b8df6e9577bc5c193e92e76da9b673dc206163b9da81efb5696aad3823
MD5 8005ab2276f03fc99be739d4851d3784
BLAKE2b-256 7aaf1b8816fd25ab18df3de83fc4642b939c02458caa55f913abee6fa071265c

See more details on using hashes here.

Provenance

The following attestation bundles were made for neural_geometry-0.1.3-py3-none-any.whl:

Publisher: release.yaml on ae-bii/neural-geometry

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