TensorNetwork for Machine Learning

TL;DR

This paper explores tensor networks for image classification, demonstrating high accuracy on MNIST datasets and significant computational speedups with GPU acceleration using the TensorNetwork library.

Contribution

It introduces a detailed method for encoding images into tensor networks and shows practical benefits in accuracy and computational efficiency.

Findings

98% accuracy on MNIST

88% accuracy on Fashion-MNIST

Over 10x speedup with GPU

Abstract

We demonstrate the use of tensor networks for image classification with the TensorNetwork open source library. We explain in detail the encoding of image data into a matrix product state form, and describe how to contract the network in a way that is parallelizable and well-suited to automatic gradients for optimization. Applying the technique to the MNIST and Fashion-MNIST datasets we find out-of-the-box performance of 98% and 88% accuracy, respectively, using the same tensor network architecture. The TensorNetwork library allows us to seamlessly move from CPU to GPU hardware, and we see a factor of more than 10 improvement in computational speed using a GPU.