Quantum Neuron: an elementary building block for machine learning on quantum computers

Abstract

Even the most sophisticated artificial neural networks are built by aggregating substantially identical units called neurons. A neuron receives multiple signals, internally combines them, and applies a non-linear function to the resulting weighted sum. Several attempts to generalize neurons to the quantum regime have been proposed, but all proposals collided with the difficulty of implementing non-linear activation functions, which is essential for classical neurons, due to the linear nature of quantum mechanics. Here we propose a solution to this roadblock in the form of a small quantum circuit that naturally simulates neurons with threshold activation. Our quantum circuit defines a building block, the "quantum neuron", that can reproduce a variety of classical neural network constructions while maintaining the ability to process superpositions of inputs and preserve quantum coherence and entanglement. In the construction of feedforward networks of quantum neurons, we provide numerical evidence that the network not only can learn a function when trained with superposition of inputs and the corresponding output, but that this training suffices to learn the function on all individual inputs separately. When arranged to mimic Hopfield networks, quantum neural networks exhibit properties of associative memory. Patterns are encoded using the simple Hebbian rule for the weights and we demonstrate attractor dynamics from corrupted inputs. Finally, the fact that our quantum model closely captures (traditional) neural network dynamics implies that the vast body of literature and results on neural networks becomes directly relevant in the context of quantum machine learning.

27 pages, 11 figures

References in corpus (6)

• Playing Atari with Deep Reinforcement Learning
• Quantum algorithm for solving linear systems of equations
• Quantum random access memory
• The quest for a Quantum Neural Network
• Quantum machine learning: a classical perspective
• Quantum generalisation of feedforward neural networks

Cited by in corpus (49)

• Barren plateaus in quantum neural network training landscapes
• Quantum Circuit Learning
• Efficient Learning for Deep Quantum Neural Networks
• Quantum generative adversarial networks
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Quantum autoencoders to denoise quantum data
• Quantum computing models for artificial neural networks
• Biology and medicine in the landscape of quantum advantages
• QReLU and m-QReLU: Two novel quantum activation functions to aid medical diagnostics
• Learning temporal data with variational quantum recurrent neural network
• Building quantum neural networks based on swap test
• Quantum classification of the MNIST dataset with Slow Feature Analysis
• Training Optimization for Gate-Model Quantum Neural Networks
• Advances in Quantum Deep Learning: An Overview
• The Efficient Preparation of Normal Distributions in Quantum Registers
• Quantum utility -- definition and assessment of a practical quantum advantage
• Quantum Superposition Inspired Spiking Neural Network
• Experimental quantum stochastic walks simulating associative memory of Hopfield neural networks
• A Simple Quantum Neural Net with a Periodic Activation Function
• Quantum Computer-Aided design of Quantum Optics Hardware
• Repeat-Until-Success circuits with fixed-point oblivious amplitude amplification
• A review of Quantum Neural Networks: Methods, Models, Dilemma
• Quantum Natural Language Processing
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning
• Recurrent Quantum Neural Networks
• Networked Quantum Services
• Phase diagram of quantum generalized Potts-Hopfield neural networks
• Entangled Quantum Memristors
• Quantized Three-Ion-Channel Neuron Model for Neural Action Potentials
• Direct implementation of a perceptron in superconducting circuit quantum hardware
• A Quantum Hopfield Associative Memory Implemented on an Actual Quantum Processor
• Quantum Cross Entropy and Maximum Likelihood Principle
• Quantum Splines for Non-Linear Approximations
• A Universal Quantum Circuit Design for Periodical Functions
• A model of interacting quantum neurons with a dynamic synapse
• Theory of Quantum Path Computing with Fourier Optics and Future Applications for Quantum Supremacy, Neural Networks and Nonlinear Schrödinger Equations
• Can biological quantum networks solve NP-hard problems?
• Distributed Memory Techniques for Classical Simulation of Quantum Circuits
• The role of coherence theory in attractor quantum neural networks
• A universal duplication-free quantum neural network
• OpticalGAN : Generative Adversarial Networks for Continuous Variable Quantum Computation
• Quantum Alphatron: quantum advantage for learning with kernels and noise
• Perspectives on Utilization of Measurements in Quantum Algorithms
• Quantum Deformed Neural Networks
• Generalization Study of Quantum Neural Network
• On the capacity of a quantum perceptron for storing biased patterns
• On quantum neural networks
• Quantum Algorithms for Unsupervised Machine Learning and Neural Networks
• Clustering and enhanced classification using a hybrid quantum autoencoder