Neural Networks Architecture Evaluation in a Quantum Computer

TL;DR

This paper introduces a quantum algorithm called QNNAE for evaluating neural network architectures, which operates without weight initialization and provides performance-based binary outputs, matching training costs.

Contribution

It presents a novel quantum algorithm for neural network evaluation that is independent of weight initialization and directly correlates output with network performance.

Findings

Quantum algorithm evaluates architectures efficiently

Outputs binary performance indicators

Cost matches neural network training

Abstract

In this work, we propose a quantum algorithm to evaluate neural networks architectures named Quantum Neural Network Architecture Evaluation (QNNAE). The proposed algorithm is based on a quantum associative memory and the learning algorithm for artificial neural networks. Unlike conventional algorithms for evaluating neural network architectures, QNNAE does not depend on initialization of weights. The proposed algorithm has a binary output and results in 0 with probability proportional to the performance of the network. And its computational cost is equal to the computational cost to train a neural network.