![](https://ccweb.imgix.net/https%3A%2F%2Fwww.classcentral.com%2Fimages%2Ficon-black-friday.png?auto=format&ixlib=php-4.1.0&s=fe56b83c82babb2f8fce47a2aed2f85d)
Overview
![](https://ccweb.imgix.net/https%3A%2F%2Fwww.classcentral.com%2Fimages%2Ficon-black-friday.png?auto=format&ixlib=php-4.1.0&s=fe56b83c82babb2f8fce47a2aed2f85d)
This course teaches about sparse and dense vector search, comparing their differences and advantages, and how the SPLADE model can enhance traditional sparse embedding methods like TF-IDF and BM25. It covers the vocabulary mismatch problem, SPLADE's functioning using transformers, masked language modeling, implementation in Python with PyTorch and Hugging Face, and its usage alongside dense embedding models. The intended audience for this course includes individuals interested in AI-powered search systems and those looking to optimize search and recommendation algorithms.
Syllabus
Sparse and dense vector search
Comparing sparse vs. dense vectors
Using sparse and dense together
What is SPLADE?
Vocabulary mismatch problem
How SPLADE works transformers 101
Masked language modeling MLM
How SPLADE builds embeddings with MLM
Where SPLADE doesn't work so well
Implementing SPLADE in Python
SPLADE with PyTorch and Hugging Face
Using the Naver SPLADE library
What's next for vector search?
Taught by
James Briggs