Weightless neural network parameters and architecture selection in a quantum computer

TL;DR

This paper introduces a quantum-based method for automatically selecting neural network parameters and architecture, leveraging quantum superposition and non-linear operators to perform a global search, reducing empirical trial-and-error.

Contribution

It presents a novel quantum learning algorithm for qWNN that enables automatic, global architecture and parameter selection, improving over traditional empirical methods.

Findings

Enables global search in qWNN architecture space

Uses quantum superposition for efficient learning

Reduces need for empirical trial-and-error

Abstract

Training artificial neural networks requires a tedious empirical evaluation to determine a suitable neural network architecture. To avoid this empirical process several techniques have been proposed to automatise the architecture selection process. In this paper, we propose a method to perform parameter and architecture selection for a quantum weightless neural network (qWNN). The architecture selection is performed through the learning procedure of a qWNN with a learning algorithm that uses the principle of quantum superposition and a non-linear quantum operator. The main advantage of the proposed method is that it performs a global search in the space of qWNN architecture and parameters rather than a local search.