TensorNetwork for Machine Learning
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.
Cite
@article{arxiv.1906.06329,
title = {TensorNetwork for Machine Learning},
author = {Stavros Efthymiou and Jack Hidary and Stefan Leichenauer},
journal= {arXiv preprint arXiv:1906.06329},
year = {2019}
}
Comments
9 pages, 8 figures. All code can be found at https://github.com/google/tensornetwork