hyperlib
Machine learning components in the hyperbolic space
Machine learning components in the hyperbolic space
To install this package, run one of the following:
This library implements common Neural Network components in the hypberbolic space (using the Poincare model). The implementation of this library uses Tensorflow as a backend and can easily be used with Keras and is meant to help Data Scientists, Machine Learning Engineers, Researchers and others to implement hyperbolic neural networks. You can also use this library for uses other than neural networks by using the mathematical functions available in the Poincare class. In the future we may implement components that can be used in models other than neural networks.
Summary
Machine learning components in the hyperbolic space
Last Updated
Jun 10, 2022 at 19:53
License
MIT
Total Downloads
22.7K
Version Downloads
17.1K
Supported Platforms
Unsupported Platforms