Hierarchical quantum classifiers

Abstract

Quantum circuits with hierarchical structure have been used to perform binary classification of classical data encoded in a quantum state. We demonstrate that more expressive circuits in the same family achieve better accuracy and can be used to classify highly entangled quantum states, for which there is no known efficient classical method. We compare performance for several different parameterizations on two classical machine learning datasets, Iris and MNIST, and on a synthetic dataset of quantum states. Finally, we demonstrate that performance is robust to noise and deploy an Iris dataset classifier on the ibmqx4 quantum computer.

References in corpus (19)

• Quantum Computing in the NISQ era and beyond
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Quantum support vector machine for big data classification
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Entanglement renormalization
• A class of quantum many-body states that can be efficiently simulated
• Time-dependent variational principle for quantum lattices
• The quest for a Quantum Neural Network
• Classical simulation of quantum many-body systems with a tree tensor network
• Quantum machine learning: a classical perspective
• Why does deep and cheap learning work so well?
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Towards Quantum Machine Learning with Tensor Networks
• Prediction by linear regression on a quantum computer
• Quantum generalisation of feedforward neural networks
• Unsupervised Machine Learning on a Hybrid Quantum Computer
• Multi-scale Entanglement Renormalization Ansatz in Two Dimensions: Quantum Ising Model
• Entanglement renormalization in fermionic systems
• Quantum circuit design for accurate simulation of qudit channels

Cited by in corpus (116)

• Parameterized quantum circuits as machine learning models
• Efficient Learning for Deep Quantum Neural Networks
• Quantum computing with neutral atoms
• Continuous-variable quantum neural networks
• An initialization strategy for addressing barren plateaus in parametrized quantum circuits
• Quantum convolutional neural network for classical data classification
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Layerwise learning for quantum neural networks
• Robust data encodings for quantum classifiers
• The Expressive Power of Parameterized Quantum Circuits
• General parameter-shift rules for quantum gradients
• Structure optimization for parameterized quantum circuits
• A divide-and-conquer algorithm for quantum state preparation
• Quantum reservoir processing
• Hardware-efficient variational quantum algorithms for time evolution
• Quantum noise protects quantum classifiers against adversaries
• Quantum Adversarial Machine Learning
• Crossing a topological phase transition with a quantum computer
• Quantum autoencoders to denoise quantum data
• Parallel Quantum Simulation of Large Systems on Small Quantum Computers
• Quantum computing models for artificial neural networks
• Realizing Quantum Convolutional Neural Networks on a Superconducting Quantum Processor to Recognize Quantum Phases
• Quantum neuromorphic computing
• Quantum Machine Learning in High Energy Physics
• Recent advances for quantum classifiers
• Variational Quantum Unsampling on a Quantum Photonic Processor
• Quantum Methods for Neural Networks and Application to Medical Image Classification
• Universal discriminative quantum neural networks
• Classical variational simulation of the Quantum Approximate Optimization Algorithm
• Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning
• Adversarial quantum circuit learning for pure state approximation
• Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
• Quantum implementation of an artificial feed-forward neural network
• Information Scrambling in Quantum Neural Networks
• Classical-to-quantum convolutional neural network transfer learning
• Reconstructing quantum states with quantum reservoir networks
• Covariant quantum kernels for data with group structure
• A Co-Design Framework of Neural Networks and Quantum Circuits Towards Quantum Advantage
• Markovian Quantum Neuroevolution for Machine Learning
• Quantum Neural Network Classifiers: A Tutorial
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Variational quantum compiling with double Q-learning
• Natural Evolutionary Strategies for Variational Quantum Computation
• Can Error Mitigation Improve Trainability of Noisy Variational Quantum Algorithms?
• Variational learning for quantum artificial neural networks
• Expressivity of Quantum Neural Networks
• A Grover-search Based Quantum Learning Scheme for Classification
• Multi-class quantum classifiers with tensor network circuits for quantum phase recognition
• Tensor networks for quantum machine learning
• Scrambling Ability of Quantum Neural Networks Architectures
• Trainability Enhancement of Parameterized Quantum Circuits via Reduced-Domain Parameter Initialization
• Predicting toxicity by quantum machine learning
• Classical versus Quantum: comparing Tensor Network-based Quantum Circuits on LHC data
• Structural risk minimization for quantum linear classifiers
• Tree tensor network classifiers for machine learning: from quantum-inspired to quantum-assisted
• Generative machine learning with tensor networks: benchmarks on near-term quantum computers
• Particle Track Reconstruction with Quantum Algorithms
• Variational quantum algorithm with information sharing
• End-to-End Quantum Machine Learning Implemented with Controlled Quantum Dynamics
• Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits
• Quantum Capsule Networks
• A Simple Quantum Neural Net with a Periodic Activation Function
• Entanglement-guided architectures of machine learning by quantum tensor network
• Variational quantum one-class classifier
• Alleviating Barren Plateaus in Parameterized Quantum Machine Learning Circuits: Investigating Advanced Parameter Initialization Strategies
• Hierarchical quantum circuit representations for neural architecture search
• Noise robustness and experimental demonstration of a quantum generative adversarial network for continuous distributions
• Topology-Driven Quantum Architecture Search Framework
• Quantum Machine Learning Tensor Network States
• Classical Splitting of Parametrized Quantum Circuits
• Harnessing Quantum Extreme Learning Machines for image classification
• Tensor networks for quantum computing
• Quantum Generative Adversarial Networks For Anomaly Detection In High Energy Physics
• Networked Quantum Services
• The Unified Effect of Data Encoding, Ansatz Expressibility and Entanglement on the Trainability of HQNNs
• Quantum Circuit AutoEncoder
• Ensemble-learning error mitigation for variational quantum shallow-circuit classifiers
• Variational Quantum Cloning: Improving Practicality for Quantum Cryptanalysis
• What can we learn from quantum convolutional neural networks?
• Quantum Continual Learning Overcoming Catastrophic Forgetting
• Simulation of memristive synapses and neuromorphic computing on a quantum computer
• Efficient MPS representations and quantum circuits from the Fourier modes of classical image data
• Decohering Tensor Network Quantum Machine Learning Models
• Optimizing Quantum Convolutional Neural Network Architectures for Arbitrary Data Dimension
• Implementation of quantum stochastic walks for function approximation, two-dimensional data classification, and sequence classification
• Quantum variational learning for entanglement witnessing
• Quantum support vector data description for anomaly detection
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• Variational Quantum Algorithms for Trace Distance and Fidelity Estimation
• F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits
• Splitting and Parallelizing of Quantum Convolutional Neural Networks for Learning Translationally Symmetric Data
• Forbidden subspaces for level-1 QAOA and IQP circuits
• Parametrized constant-depth quantum neuron
• Qubit-efficient Variational Quantum Algorithms for Image Segmentation
• A Post-Training Approach for Mitigating Overfitting in Quantum Convolutional Neural Networks
• Speedy Contraction of ZX Diagrams with Triangles via Stabiliser Decompositions
• Variational quantum eigensolver with embedded entanglement using a tensor-network ansatz
• Precise Image Generation on Current Noisy Quantum Computing Devices
• Quantum Inception Score
• Image Classification by Throwing Quantum Kitchen Sinks at Tensor Networks
• Learning Equivariant Maps with Variational Quantum Circuits
• Quantum Neural Networks in Practice: A Comparative Study with Classical Models from Standard Data Sets to Industrial Images
• Quantum tensor network algorithms for evaluation of spectral functions on quantum computers
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• Detecting Entanglement Generating Circuits in Cloud-Based Quantum Computing
• A Unified Framework for Quantum Supervised Learning
• Scaling of contraction costs for entanglement renormalization algorithms including tensor Trotterization and variational Monte Carlo
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits
• Implications of Deep Circuits in Improving Quality of Quantum Question Answering
• Multi-channel convolutional neural quantum embedding
• A quantum machine learning classifier to search for new physics
• Quantum-data-driven dynamical transition in quantum learning
• Entanglement renormalization for quantum fields with boundaries and defects
• Tucker iterative quantum state preparation
• Schmidt quantum compressor
• FRQI Pairs method for image classification using Quantum Recurrent Neural Network