Unitary quantum perceptron as efficient universal approximator

Abstract

We demonstrate that it is possible to implement a quantum perceptron with a sigmoid activation function as an efficient, reversible many-body unitary operation. When inserted in a neural network, the perceptron's response is parameterized by the potential exerted by other neurons. We prove that such a quantum neural network is a universal approximator of continuous functions, with at least the same power as classical neural networks. While engineering general perceptrons is a challenging control problem --also defined in this work--, the ubiquitous sigmoid-response neuron can be implemented as a quasi-adiabatic passage with an Ising model. In this construct, the scaling of resources is favorable with respect to the total network size and is dominated by the number of layers. We expect that our sigmoid perceptron will have applications also in quantum sensing or variational estimation of many-body Hamiltonians.

6 pages, 4 figures + (5 pages, 4 figure)

References in corpus (7)

• An introduction to quantum machine learning
• The quest for a Quantum Neural Network
• Quantum Data Fitting
• Quantum-enhanced machine learning
• Experimental implementation of an adiabatic quantum optimization algorithm
• Noise Resistant Quantum Control Using Dynamical Invariants
• Action-Noise-Assisted Quantum Control

Cited by in corpus (46)

• Noisy intermediate-scale quantum (NISQ) algorithms
• Parameterized quantum circuits as machine learning models
• Shortcuts to adiabaticity: concepts, methods, and applications
• Efficient Learning for Deep Quantum Neural Networks
• Data re-uploading for a universal quantum classifier
• Continuous-variable quantum neural networks
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Is quantum advantage the right goal for quantum machine learning?
• Trainability of Dissipative Perceptron-Based Quantum Neural Networks
• Quantum autoencoders to denoise quantum data
• Quantum computing models for artificial neural networks
• Gaussian states of continuous-variable quantum systems provide universal and versatile reservoir computing
• Universal Approximation Property of Quantum Machine Learning Models in Quantum-Enhanced Feature Spaces
• Quantum Neural Network for Quantum Neural Computing
• Quantum implementation of an artificial feed-forward neural network
• Information Scrambling in Quantum Neural Networks
• Training Optimization for Gate-Model Quantum Neural Networks
• Quantum machine learning and quantum biomimetics: A perspective
• Experimental quantum advantage with quantum coupon collector
• Variational learning for quantum artificial neural networks
• Expressivity of Quantum Neural Networks
• Quantum Error Correction with Quantum Autoencoders
• Scrambling Ability of Quantum Neural Networks Architectures
• Quantum Superposition Inspired Spiking Neural Network
• Entanglement entropy production in Quantum Neural Networks
• Quantum computing model of an artificial neuron with continuously valued input data
• Quantum neural networks force fields generation
• A duplication-free quantum neural network for universal approximation
• Speed-up Quantum Perceptron via Shortcuts to Adiabaticity
• Phase diagram of quantum generalized Potts-Hopfield neural networks
• The Unified Effect of Data Encoding, Ansatz Expressibility and Entanglement on the Trainability of HQNNs
• Simulation of a Variational Quantum Perceptron using Grover's Algorithm
• A Quantum Hopfield Associative Memory Implemented on an Actual Quantum Processor
• A quantum collisional classifier driven by information reservoir
• Optimal storage capacity of quantum Hopfield neural networks
• Direct implementation of a perceptron in superconducting circuit quantum hardware
• Universal quantum gates, artificial neurons and pattern recognition simulated by \textit{LC} resonators
• Minimal action control method in quantum critical models
• A model of interacting quantum neurons with a dynamic synapse
• Quadratic Quantum Speedup for Perceptron Training
• Quantum neural networks with multi-qubit potentials
• Measurement-based quantum machine learning
• An Amplitude-Based Implementation of the Unit Step Function on a Quantum Computer
• Dissipative learning of a quantum classifier
• On the capacity of a quantum perceptron for storing biased patterns
• Pseudo quantum advantages in perceptron storage capacity