GloVe - Python for Word Representation
summary
Shows how to use glove-python (the C implementation wrapped for Python) with a window of 10 and 100–200 dimensions, including loading Stanford’s pretrained 200-d vectors trained on ~6 million tokens. Trains on cleaned text and on a healthcare sequence dataset of ~80,000 patient records (diagnosis/procedure codes), then runs k-means on embeddings to surface comorbidity clusters — finds diabetes clustering with seizures, colon cancer and mental‑health codes. Demonstrates vector arithmetic like king - man + woman = queen and saving/loading models.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 1:42Python Block
- 5:38Concept
- 6:51Matrix
- 10:24package
- 14:02Word vectors
- 16:44Mathematical operations
- 16:57Mathematical analogy
- 20:41Examples
- 23:20Healthcare
- 27:14Diabetes
- 30:18Deep Learning
related talks
34mLearning about AI/ML for Text, with Wordle!
47mInside GPT – Large Language Models Demystified
01h 40mA Deep Dive into NLP with PyTorch
34mWord Embeddings for fun and profit in Gensim
39mBeyond word2vec: GloVe, fastText, StarSpace
01h 38mNavigating the World of NLP and Text Analytics
31mTaking AI/ML to the next level: Text!
28m"Embeddings: How Computers Learned to Read"