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

TL;DR

This paper introduces a quantum neuron model that overcomes the challenge of implementing non-linear activation functions in quantum computing, enabling quantum neural networks to learn, process superpositions, and exhibit associative memory.

Contribution

The authors propose a quantum circuit that simulates neurons with threshold activation, allowing classical neural network features to be realized on quantum computers while maintaining quantum coherence.

Findings

Quantum neurons can learn functions from superposed inputs.

Quantum neural networks exhibit associative memory properties.

The model aligns quantum dynamics with classical neural network behavior.

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.