Jaan Altosaar
Graduate Student, Department of Physics, Princeton University
Talk recording
Embedding models are used in production for Google Search, in the Discover Weekly recommendation system at Spotify, and for learning representations of biological systems like genes and proteins. In this work, we develop an embedding model for foods based on patterns in a large recipe dataset. A recommendation system for food is built based on the embedding model, and we show that our model learns concepts such as which foods are complementary or which foods can be substituted for each other in recipes. The code and data are open source and readily extendable to new kinds of data.
About the speaker
Jaan is a graduate student advised by David Blei at Columbia and Shivaji Sondhi at Princeton, supported by an NSERC fellowship from Canada. His research focuses on using embedding models to study diverse data such as equations, music, and food. He has also helped develop new techniques for inference that use operators such as the Schrödinger Hamiltonian to do variational inference. His website is jaan.io.
Share this page:
