TensorNetwork for Machine Learning

Tensor networks have seen numerous applications in the physical sciences [2-34], but there has been significant progress recently in applying the same methods to problems in machine learning [35-45]. The TensorNetwork library [1] was created to facilitate this research and accelerate the adoption of tensor network methods by the ML community. In a previous paper [46] we showed how TensorNetwork could be used in a physics setting. Here we are going to illustrate how to use a matrix product state (MPS) tensor network to classify MNIST and Fashion-MNIST images. The basic technique was applied to the MNIST dataset by Stoudenmire and Schwab [35], who adapted the DMRG algorithm from physics [3] to train the network.