cair/TextUnderstandingTsetlinMachine
Using the Tsetlin Machine to learn human-interpretable rules for high-accuracy text categorization with medical applications
This project helps healthcare professionals and researchers analyze large volumes of text, like patient notes or medical research, to automatically categorize them. You provide labeled text data, and it outputs a set of easy-to-understand rules for classification, such as 'if "rash" and "reaction" and "penicillin" then Allergy.' This is ideal for medical experts, data analysts in healthcare, or researchers who need to understand why a document is categorized a certain way.
No commits in the last 6 months.
Use this if you need to classify text data with high accuracy and understand the exact rules or features that led to each classification, particularly in sensitive domains like medicine.
Not ideal if you prioritize maximum raw accuracy over interpretability and are comfortable with 'black box' models, or if you do not have access to NVIDIA GPUs and CUDA.
Stars
51
Forks
13
Language
Cuda
License
—
Category
Last pushed
Sep 09, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/cair/TextUnderstandingTsetlinMachine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
giacbrd/ShallowLearn
An experiment about re-implementing supervised learning models based on shallow neural network...
javedsha/text-classification
Machine Learning and NLP: Text Classification using python, scikit-learn and NLTK
Wluper/edm
Python package for understanding the difficulty of text classification datasets. (in CoNNL 2018)
chicago-justice-project/article-tagging
Natural Language Processing of Chicago news articles
fendouai/Awesome-Text-Classification
Awesome-Text-Classification Projects,Papers,Tutorial .