Classifying data using near-term quantum devices

DOI10.1142/S0219749918400014MaRDI QIDQ4620283zbMATH OpenWikidataFDO

Authors Johannes Bausch

Publication date 8 February 2019

Published in International Journal of Quantum Information (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1807.00804

zbMATH Keywords

neural networksdata classificationlocal Hamiltoniansground spaces

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Searching and sorting (68P10) Quantum computation (81P68) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: The goal of this work is to define a notion of a quantum neural network to classify data, which exploits the low energy spectrum of a local Hamiltonian. As a concrete application, we build a binary classifier, train it on some actual data and then test its performance on a simple classification task. More specifically, we use Microsoft's quantum simulator, Liquid, to construct local Hamiltonians that can encode trained classifier functions in their ground space, and which can be probed by measuring the overlap with test states corresponding to the data to be classified. To obtain such a classifier Hamiltonian, we further propose a training scheme based on quantum annealing which is completely closed-off to the environment and which does not depend on external measurements until the very end, avoiding unnecessary decoherence during the annealing procedure. For a network of size n, the trained network can be stored as a list of O(n) coupling strengths. We address the question of which interactions are most suitable for a given classification task, and develop a qubit-saving optimization for the training procedure on a simulated annealing device. Furthermore, a small neural network to classify colors into red vs. blue is trained and tested, and benchmarked against the annealing parameters.

Recommendations

• Supervised learning with a quantum classifier using multi-level systems
• A QUANTUM NEURAL NETWORK MODEL
• Basic quantum circuits for classification and approximation tasks
• A steady state quantum classifier
• A quantum-inspired version of the classification problem

Cites work

• Complexity classification of local Hamiltonian problems
• Complexity classification of two-qubit commuting Hamiltonians
• Frustration free gapless Hamiltonians for matrix product states
• Matrix product state representations
• On the Complexity of Commuting Local Hamiltonians, and Tight Conditions for Topological Order in Such Systems
• On the Product of Semi-Groups of Operators
• PRMLT
• Pattern recognition and machine learning.
• Supercritical entanglement in local systems: counterexample to the area law for quantum matter
• The complexity of quantum spin systems on a two-dimensional square lattice
• The power of quantum systems on a line
• The quest for a quantum neural network
• The road to quantum computational supremacy
• Universal Quantum Simulators
• Universal quantum Hamiltonians
• Upper bounds for reversible circuits based on Young subgroups

Cited in

(8)

• Quantum error reduction with deep neural network applied at the post-processing stage
• RGB image classification with quantum convolutional ansatz
• Supervised learning with a quantum classifier using multi-level systems
• Matrix product state-based quantum classifier
• Clustering by quantum annealing on the three-level quantum elements qutrits
• Basic quantum circuits for classification and approximation tasks
• Variational convolutional neural networks classifiers
• Classification Problem in a Quantum Framework

Describes a project that uses

Uses Software

• PRMLT
• LIQUi
• Adam

This page was built for publication: Classifying data using near-term quantum devices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4620283)