 |
Center for Nonlinear Studies |
In this talk I will discuss several SVD-based tensor decompositions (like tensor train), related algorithm and outline several recent works that connect tensor decomposition and machine learning. In short, tensor decompositions (and in general, factorization methods) can be very efficient in machine learning for different tasks, for the compression of neural networks, for the neural architectures, and also for the design of new machine learning models.
Host: Ben Nebgen