Entanglement and Tensor Networks for Supervised Image Classification

by   John Martyn, et al.

Tensor networks, originally designed to address computational problems in quantum many-body physics, have recently been applied to machine learning tasks. However, compared to quantum physics, where the reasons for the success of tensor network approaches over the last 30 years is well understood, very little is yet known about why these techniques work for machine learning. The goal of this paper is to investigate entanglement properties of tensor network models in a current machine learning application, in order to uncover general principles that may guide future developments. We revisit the use of tensor networks for supervised image classification using the MNIST data set of handwritten digits, as pioneered by Stoudenmire and Schwab [Adv. in Neur. Inform. Proc. Sys. 29, 4799 (2016)]. Firstly we hypothesize about which state the tensor network might be learning during training. For that purpose, we propose a plausible candidate state |Σ_ℓ⟩ (built as a superposition of product states corresponding to images in the training set) and investigate its entanglement properties. We conclude that |Σ_ℓ⟩ is so robustly entangled that it cannot be approximated by the tensor network used in that work, which must therefore be representing a very different state. Secondly, we use tensor networks with a block product structure, in which entanglement is restricted within small blocks of n × n pixels/qubits. We find that these states are extremely expressive (e.g. training accuracy of 99.97 % already for n=2), suggesting that long-range entanglement may not be essential for image classification. However, in our current implementation, optimization leads to over-fitting, resulting in test accuracies that are not competitive with other current approaches.


page 1

page 2

page 3

page 4


Machine Learning by Two-Dimensional Hierarchical Tensor Networks: A Quantum Information Theoretic Perspective on Deep Architectures

The resemblance between the methods used in studying quantum-many body p...

Quantum Phase Recognition using Quantum Tensor Networks

Machine learning (ML) has recently facilitated many advances in solving ...

Entangled q-Convolutional Neural Nets

We introduce a machine learning model, the q-CNN model, sharing key feat...

Deep convolutional tensor network

Tensor networks are linear algebraic representations of quantum many-bod...

Tensor network to learn the wavefunction of data

How many different ways are there to handwrite digit 3? To quantify this...

Bridging Many-Body Quantum Physics and Deep Learning via Tensor Networks

The harnessing of modern computational abilities for many-body wave-func...

Tensor-networks for High-order Polynomial Approximation: A Many-body Physics Perspective

We analyze the problem of high-order polynomial approximation from a man...

Please sign up or login with your details

Forgot password? Click here to reset