Completely Quantum Neural Networks

Abstract

Artificial neural networks are at the heart of modern deep learning algorithms. We describe how to embed and train a general neural network in a quantum annealer without introducing any classical element in training. To implement the network on a state-of-the-art quantum annealer, we develop three crucial ingredients: binary encoding the free parameters of the network, polynomial approximation of the activation function, and reduction of binary higher-order polynomials into quadratic ones. Together, these ideas allow encoding the loss function as an Ising model Hamiltonian. The quantum annealer then trains the network by finding the ground state. We implement this for an elementary network and illustrate the advantages of quantum training: its consistency in finding the global minimum of the loss function and the fact that the network training converges in a single annealing step, which leads to short training times while maintaining a high classification performance. Our approach opens a novel avenue for the quantum training of general machine learning models.

arXiv comment12 pages, 6 figures

References in corpus (27)

• A variational eigenvalue solver on a quantum processor
• Quantum Annealing in the Transverse Ising Model
• The theory of variational hybrid quantum-classical algorithms
• Adiabatic Quantum Computing
• Circuit-centric quantum classifiers
• Quantum Annealing: A New Method for Minimizing Multidimensional Functions
• Transfer learning in hybrid classical-quantum neural networks
• Continuous-variable quantum neural networks
• Computational Role of Multiqubit Tunneling in a Quantum Annealer
• Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
• Entanglement in a quantum annealing processor
• Prospects for Quantum Enhancement with Diabatic Quantum Annealing
• Consistency Tests of Classical and Quantum Models for a Quantum Annealer
• Exact Ising model simulation on a quantum computer
• Anomaly detection in high-energy physics using a quantum autoencoder
• Search for anomalous t t-bar production in the highly-boosted all-hadronic final state
• Search for heavy particles decaying into top-quark pairs using lepton-plus-jets events in proton-proton collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Quantum Machine Learning for Particle Physics using a Variational Quantum Classifier
• Bayesian Network Structure Learning Using Quantum Annealing
• On the Quantum versus Classical Learnability of Discrete Distributions
• Tunneling and speedup in quantum optimization for permutation-symmetric problems
• Search for heavy particles decaying into a top-quark pair in the fully hadronic final state in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Dissipation in adiabatic quantum computers: Lessons from an exactly solvable model
• Event Classification with Quantum Machine Learning in High-Energy Physics
• Maximum-Entropy Inference with a Programmable Annealer
• A dissipative environment may improve the quantum annealing performances of the ferromagnetic p-spin model
• Quantum adiabatic machine learning with zooming

Cited by in corpus (12)

• Classical surrogates for quantum learning models
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• FEqa: Finite Element Computations on Quantum Annealers
• Simulating quantum field theories on continuous-variable quantum computers
• Quantum Annealing for Neural Network optimization problems: a new approach via Tensor Network simulations
• Nonnegative/Binary Matrix Factorization for Image Classification using Quantum Annealing
• Towards a Quantum Simulation of Nonlinear Sigma Models with a Topological Term
• Jet Discrimination with Quantum Complete Graph Neural Network
• QFitter -- A Quantum Fitting Framework Applied to Effective Field Theories
• 1 Particle - 1 Qubit: Particle Physics Data Encoding for Quantum Machine Learning
• Benchmarking of quantum fidelity kernels for Gaussian process regression
• Ancillary entangling Floquet kicks for accelerating quantum algorithms