In this talk I will present two deep learning-based algorithms for representation learning.
In the first half of the talk I will present SpectralNet, a deep learning approach for spectral clustering, which is scalable and allows for straight-forward out of sample extension.
In the second half of the talk I will present a deep learning approach for recovery of a single independent component of interest, given another component as a condition.
Uri Shaham holds a Ph.D in Statistics from Yale University, under the supervision of profs. Ronald Coifman, Sahand Negahban and Yuval Kluger. Since his graduation in 2017 he is affiliated with Yale's center for outcome research and evaluation as an assistant professor adjunct. Alongside his academic endeavours, he has also worked for several years in the industry, in various algorithms and machine learning research roles.