Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with predefined topics from an unlabeled document corpus.
Code created for blog series on unsupervised feature/topic extraction from corporate email content. An implementation for cleaning raw email content, data analysis, unsupervised topic clustering for sentiment/alignment and ultimately several deep-learning models for classification. Details at www.avemacconsulting.com.
A project leveraging machine learning for the identification and classification of glomeruli in renal biopsy images. Utilizes SegNet and U-Net for segmentation and explores unsupervised clustering for sclerosed glomeruli classification
Assignments in 'Applied Probabilistic Models' course by Prof. Ido Dagan at Bar-Ilan University.
Python pipeline for Metrological Domain Profiling (MDP) of ancient administrative scripts (Proto-Cuneiform, Proto-Elamite, and Indus Valley). Achieves 100% metrological classification accuracy and maps Indus sign-iconography semantic locks.
Copula-based pairwise Markov chains for non-Gaussian time-series classification, estimation, imputation and forecasting.
To associate your repository with the unsupervised-classification topic, visit your repo's landing page and select "manage topics."