Quantum generalisation of feedforward neural networks

Abstract

We propose a quantum generalisation of a classical neural network. The classical neurons are firstly rendered reversible by adding ancillary bits. Then they are generalised to being quantum reversible, i.e.\ unitary. (The classical networks we generalise are called feedforward, and have step-function activation functions.) The quantum network can be trained efficiently using gradient descent on a cost function to perform quantum generalisations of classical tasks. We demonstrate numerically that it can: (i) compress quantum states onto a minimal number of qubits, creating a quantum autoencoder, and (ii) discover quantum communication protocols such as teleportation. Our general recipe is theoretical and implementation-independent. The quantum neuron module can naturally be implemented photonically.

References in corpus (9)

• Quantum algorithm for solving linear systems of equations
• An introduction to quantum machine learning
• The quest for a Quantum Neural Network
• Quantum Data Fitting
• Quantum-enhanced machine learning
• Polarization entangled state measurement on a chip
• Quantum learning of coherent states
• Strain-optic active control for quantum integrated photonics
• Hyperspherical Parameterization of Unitary Matrices

Cited by in corpus (113)

• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Noisy intermediate-scale quantum (NISQ) algorithms
• Quantum machine learning in feature Hilbert spaces
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Efficient Learning for Deep Quantum Neural Networks
• Challenges and Opportunities in Quantum Machine Learning
• Data re-uploading for a universal quantum classifier
• Hybrid quantum-classical algorithms and quantum error mitigation
• Quantum machine learning: a classical perspective
• Generalization in quantum machine learning from few training data
• Continuous-variable quantum neural networks
• Hierarchical quantum classifiers
• Experimental Quantum Generative Adversarial Networks for Image Generation
• An Artificial Neuron Implemented on an Actual Quantum Processor
• The prospects of quantum computing in computational molecular biology
• Quantum Hopfield neural network
• Quantum Variational Autoencoder
• Quantum generative adversarial network for generating discrete distribution
• Quantum Machine Learning for Chemistry and Physics
• Quantum Adversarial Machine Learning
• Quantum autoencoders to denoise quantum data
• Quantum Neuron: an elementary building block for machine learning on quantum computers
• Machine learning of noise-resilient quantum circuits
• Optimizing quantum optimization algorithms via faster quantum gradient computation
• Experimental Realization of a Quantum Autoencoder: The Compression of Qutrits via Machine Learning
• Unitary quantum perceptron as efficient universal approximator
• Biology and medicine in the landscape of quantum advantages
• Basic protocols in quantum reinforcement learning with superconducting circuits
• Universal discriminative quantum neural networks
• Supervised learning with a quantum classifier using a multi-level system
• Quantum Neural Network for Quantum Neural Computing
• Quantum implementation of an artificial feed-forward neural network
• Building quantum neural networks based on swap test
• Quantum machine learning for data scientists
• Quantum autoencoders via quantum adders with genetic algorithms
• Realization of a quantum autoencoder for lossless compression of quantum data
• A Co-Design Framework of Neural Networks and Quantum Circuits Towards Quantum Advantage
• Noise-Assisted Quantum Autoencoder
• Training Optimization for Gate-Model Quantum Neural Networks
• Markovian Quantum Neuroevolution for Machine Learning
• Quantum machine learning and quantum biomimetics: A perspective
• Nonlinear Quantum Neuron: A Fundamental Building Block for Quantum Neural Networks
• Resonant Quantum Principal Component Analysis
• Advances in Quantum Deep Learning: An Overview
• Experimental quantum advantage with quantum coupon collector
• Natural Evolutionary Strategies for Variational Quantum Computation
• Detecting and quantifying entanglement on near-term quantum devices
• Practical distributed quantum information processing with LOCCNet
• ResQNets: A Residual Approach for Mitigating Barren Plateaus in Quantum Neural Networks
• Universal Adversarial Examples and Perturbations for Quantum Classifiers
• Experimental Implementation of a Quantum Autoencoder via Quantum Adders
• Neural network-based prediction of the secret-key rate of quantum key distribution
• Experimental quantum stochastic walks simulating associative memory of Hopfield neural networks
• Noise robustness and experimental demonstration of a quantum generative adversarial network for continuous distributions
• A review of Quantum Neural Networks: Methods, Models, Dilemma
• Generic detection-based error-mitigation using quantum autoencoders
• A duplication-free quantum neural network for universal approximation
• Entanglement-based quantum deep learning
• Optimal quantum dataset for learning a unitary transformation
• Speed-up Quantum Perceptron via Shortcuts to Adiabaticity
• Supervised Learning with Quantum Measurements
• Estimating Quantum Mutual Information Through a Quantum Neural Network
• Quantum adaptive agents with efficient long-term memories
• Quantum Circuit AutoEncoder
• The Unified Effect of Data Encoding, Ansatz Expressibility and Entanglement on the Trainability of HQNNs
• Quantifying scrambling in quantum neural networks
• Quantum correlation alignment for unsupervised domain adaptation
• Quantum Machine Learning Implementations: Proposals and Experiments
• Jarzynski-like Equality of Nonequilibrium Information Production Based on Quantum Cross Entropy
• Realization of a quantum neural network using repeat-until-success circuits in a superconducting quantum processor
• Experimental demonstration of quantum learning speed-up with classical input data
• Simulation of memristive synapses and neuromorphic computing on a quantum computer
• A quantum collisional classifier driven by information reservoir
• Implementation of quantum stochastic walks for function approximation, two-dimensional data classification, and sequence classification
• Quantum subspace alignment for domain adaptation
• Parametric Probabilistic Quantum Memory
• Generative model for learning quantum ensemble via optimal transport loss
• Continuous-variable quantum kernel method on a programmable photonic quantum processor
• Quantum-enhanced neural networks in the neural tangent kernel framework
• Quantum Generative Adversarial Networks in a Silicon Photonic Chip with Maximum Expressibility
• Implementing perceptron models with qubits
• Quantum inspired qubit qutrit neural networks for real time financial forecasting
• Image Compression and Classification Using Qubits and Quantum Deep Learning
• Pattern capacity of a single quantum perceptron
• Quantum autoencoders using mixed reference states
• A Study on Quantum Graph Neural Networks Applied to Molecular Physics
• Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics
• An example of use of Variational Methods in Quantum Machine Learning
• Quantum Darwinism and the spreading of classical information in non-classical theories
• Probing arbitrary polarized photon pairs undergoing double Compton scatterings by a dedicated MC simulator validated with experimental data
• Experimentally detecting a quantum change point via Bayesian inference
• Can biological quantum networks solve NP-hard problems?
• Rigorous noise reduction with quantum autoencoders
• Information compression via hidden subgroup quantum autoencoders
• Learning Simon's quantum algorithm
• Experimental benchmarking of quantum state overlap estimation strategies with photonic systems
• State Classification via a Random-Walk-Based Quantum Neural Network
• An Amplitude-Based Implementation of the Unit Step Function on a Quantum Computer
• Dissipative learning of a quantum classifier
• Reinforcement learning to learn quantum states for Heisenberg scaling accuracy
• Parameterized quantum comb and simpler circuits for reversing unknown qubit-unitary operations
• Guided Graph Compression for Quantum Graph Neural Networks
• Neural networks with quantum states of light
• On quantum ensembles of quantum classifiers
• Generalization Study of Quantum Neural Network
• Clustering and enhanced classification using a hybrid quantum autoencoder
• Moments of Quantum Channel Ensembles
• Quantum relaxed row and column iteration methods based on block-encoding
• Pseudo quantum advantages in perceptron storage capacity
• State transfer with separable optical beams and variational quantum algorithms with classical light
• Quantum Algorithms for State Preparation and Data Classification based on Stabilizer Codes
• Disentangling quantum autoencoder