scikit-cuda VS tmu

I found this lovely repo -> https://github.com/lebedov/scikit-cuda

Code: https://github.com/cair/tmu

Quick Read: https://www.marktechpost.com/2023/01/10/this-artificial-intelligence-ai-research-from-norway-introduces-tsetlin-machine-based-autoencoder-for-representing-words-using-logical-expressions/ Paper: https://arxiv.org/pdf/2301.00709.pdf Github: https://github.com/cair/tmu

Here is a new self-supervised machine learning approach that captures word meaning with concise logical expressions. The logical expressions consist of contextual words like “black,” “cup,” and “hot” to define other words like “coffee,” thus being human-understandable. I raise the question in the heading because our logical embedding performs competitively on several intrinsic and extrinsic benchmarks, matching pre-trained GLoVe embeddings on six downstream classification tasks. Thanks to my clever PhD student Bimal, we now have even more fun and exciting research ahead of us. Our long term research goal is, of course, to provide an energy efficient and transparent alternative to deep learning. You find the paper here: https://arxiv.org/abs/2301.00709 , an implementation of the Tsetlin Machine Autoencoder here: https://github.com/cair/tmu, and a simple word embedding demo here: https://github.com/cair/tmu/blob/main/examples/IMDbAutoEncoderDemo.py.