Quantum computing model of an artificial neuron with continuously valued input data

TL;DR

This paper extends a quantum artificial neuron model to handle continuous input data, enabling more effective integration with automatic differentiation learning methods for quantum neural networks.

Contribution

It generalizes a previous quantum neuron design to accept continuous inputs without increasing qubit count, facilitating advanced training techniques.

Findings

Supports continuous input data encoding in quantum neurons

Enables automatic differentiation for quantum neural networks

Maintains qubit efficiency in the generalized model

Abstract

Artificial neural networks have been proposed as potential algorithms that could benefit from being implemented and run on quantum computers. In particular, they hold promise to greatly enhance Artificial Intelligence tasks, such as image elaboration or pattern recognition. The elementary building block of a neural network is an artificial neuron, i.e. a computational unit performing simple mathematical operations on a set of data in the form of an input vector. Here we show how the design for the implementation of a previously introduced quantum artificial neuron [npj Quant. Inf. $\textbf{5}$, 26], which fully exploits the use of superposition states to encode binary valued input data, can be further generalized to accept continuous -- instead of discrete-valued input vectors, without increasing the number of qubits. This further step is crucial to allow for a direct application of an automatic differentiation learning procedure, which would not be compatible with binary-valued data encoding.