As an undergraduate, I stumbled upon the fascinating paper on Tversky Neural Networks and decided to take on the challenge of reproducing it. My goal was to create a faithful implementation of the paper and share it with the community as a small library for others to use and experiment with.
The journey was not easy, but I’m excited to share my progress so far. I’ve pushed my implementation to PyPI and GitHub, and I’m looking for feedback from the community on the math and any inconsistencies with the paper and my code.
You can find my implementation on PyPI:
Note that this library is still under very active development, and I have a lot of things left to do. But I’m committed to seeing it through and making it a valuable resource for the community.