scikit-cuda
tmu
scikit-cuda | tmu | |
---|---|---|
1 | 5 | |
968 | 109 | |
- | 2.8% | |
2.5 | 9.2 | |
7 months ago | about 1 month ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
scikit-cuda
-
GPU Based Kernel-PCA
I found this lovely repo -> https://github.com/lebedov/scikit-cuda
tmu
- Tsetlin machine – the other AI toolbooks
- Tsetlin Machine Unified (TMU) - One Codebase to Rule Them All
-
[R] New Tsetlin machine learning scheme creates up to 80x smaller logical rules, benefitting hardware efficiency and interpretability.
Code: https://github.com/cair/tmu
-
This Artificial Intelligence (AI) Research From Norway Introduces Tsetlin Machine-Based Autoencoder For Representing Words Using Logical Expressions
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
-
Do we really need 300 floats to represent the meaning of a word? Representing words with words - a logical approach to word embedding using a self-supervised Tsetlin Machine Autoencoder.
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.
What are some alternatives?
cupy - NumPy & SciPy for GPU
nvitop - An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
cuml - cuML - RAPIDS Machine Learning Library
chainer - A flexible framework of neural networks for deep learning
PyCUDA - CUDA integration for Python, plus shiny features
pyopencl - OpenCL integration for Python, plus shiny features
kernel_tuner - Kernel Tuner
TsetlinMachine - Code and datasets for the Tsetlin Machine
cusim - Superfast CUDA implementation of Word2Vec and Latent Dirichlet Allocation (LDA)
catboost - A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.