The Rise of the Vector Database
Modern Machine Learning (ML) represents everything as vectors, from documents, to videos, to user behavior. This representation makes it possible to accurately search, retrieve, rank, and classify different items by similarity and relevance. Running real-time applications that rely on large numbers of such high dimensional vectors requires a dedicated data infrastructure called a Vector Database. In this talk we will discuss the need for such infrastructure, the algorithmic and engineering challenges in building a vector database, and open problems we still have no adequate solutions for. Time permits, I will introduce Pinecone, the first serverless vector database.
Edo is the Founder-CEO of Pinecone. Before Pinecone was a Director at AWS and the head of Amazon AI Labs and a Senior Director at Yahoo running the scalable Machine Learning Platforms group. He holds a PhD in Computer Science from Yale University and a B.Sc. in Physics and Computer Science from Tel Aviv University. He was also a postdoctoral fellow in Applied Mathematics at Yale and an adjunct professor at Tel Aviv University. He is the author of more than 75 academic papers and patents on topics such as machine learning, systems, and optimization.