Tag: machine-learning
All the articles with the tag "machine-learning".
-
Vector Databases: A Survey of the Landscape
A complete survey of the vector database landscape — from ANN algorithms and indexing libraries like FAISS and Annoy, to open-source databases like Milvus, Qdrant and Weaviate, to managed vendor services. Plus a real-world case study on how to choose one.
-
Trained a Transaction Foundation Model from Scratch on 2×RTX 4090
Trained a 29M-parameter Llama decoder on financial transaction data from scratch on 2×RTX 4090s. Extracted embeddings and got +32% lift on fraud detection with XGBoost. End-to-end pipeline in 18 minutes.
-
Face Recognition on the Olivetti Dataset (Eigenfaces)
Using PCA and eigenfaces for face recognition on the classic Olivetti dataset.