DeepAI AI Chat
Log In Sign Up

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

by   Ding Liu, et al.

The resemblance between the methods used in studying quantum-many body physics and in machine learning has drawn considerable attention. In particular, tensor networks (TNs) and deep learning architectures bear striking similarities to the extent that TNs can be used for machine learning. Previous results used one-dimensional TNs in image recognition, showing limited scalability and a high bond dimension. In this work, we train two-dimensional hierarchical TNs to solve image recognition problems, using a training algorithm derived from the multipartite entanglement renormalization ansatz (MERA). This approach overcomes scalability issues and implies novel mathematical connections among quantum many-body physics, quantum information theory, and machine learning. While keeping the TN unitary in the training phase, TN states can be defined, which optimally encodes each class of the images into a quantum many-body state. We study the quantum features of the TN states, including quantum entanglement and fidelity. We suggest these quantities could be novel properties that characterize the image classes, as well as the machine learning tasks. Our work could be further applied to identifying possible quantum properties of certain artificial intelligence methods.


Entanglement and Tensor Networks for Supervised Image Classification

Tensor networks, originally designed to address computational problems i...

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

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

On the Equivalence of Restricted Boltzmann Machines and Tensor Network States

Restricted Boltzmann machine (RBM) is one of the fundamental building bl...

Quantum Phase Recognition using Quantum Tensor Networks

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

Surveying structural complexity in quantum many-body systems

Quantum many-body systems exhibit a rich and diverse range of exotic beh...

Machine learning for many-body physics: The case of the Anderson impurity model

Machine learning methods are applied to finding the Green's function of ...

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

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

Code Repositories



view repo