an introduction to approximate nearest neighbors
summary
Explains HNSW (hierarchical navigable small world) as a layered graph index that finds neighbors by greedy descent, claiming sublinear search via layered graphs and tunable recall for approximate nearest neighbors. Describes using neural embeddings from HuggingFace / sentence‑transformers, shows a geo example where filtering changes the chosen airport, and notes an implementation: Quadrant open‑source vector DB using HNSW with built‑in filtering.
AI-written summary · about
related talks
49mSpectral Approaches to Nearest Neighbor Search
54mDissimilarity search...
50mA fun and absurd introduction to Vector Databases
47mNeural Search Comes to Apache Solr: Approximate Nearest Neighbor, BERT & more
44mVector Search Beyond the Hype: Real-World Implementation and Performance Insights
38mSearch: A New Era
24mIntroduction to Vector Search with Weaviate
01h 05mNearest Neighbor Methods I