Quantum Neural Network Training Algorithm

Kerstin Beer, Müller, Gabriel

Noisy intermediate-scale quantum (NISQ) devices build the first generation of quantum computers. Quantum neural networks (QNNs) gained high interest as one of the few suitable quantum algorithms to run on these NISQ devices. Most of the QNNs exploit supervised training algorithms with quantum states in form of pairs to learn their underlying relation. However, only little attention has been given to unsupervised training algorithms despite interesting applications where the quantum data does not occur in pairs. Here we propose an approach to unsupervised learning and reproducing characteristics of any given set of quantum states. We build a generative adversarial model using two dissipative quantum neural networks (DQNNs), leading to the dissipative quantum generative adversarial network (DQGAN). The generator DQNN aims to produce quantum states similar to the training data while the discriminator DQNN aims to distinguish the generator's output from the training data. We find that training both parts in a competitive manner results in a well trained generative DQNN. We see our contribution as a proof of concept for using DQGANs to learn and extend unlabeled training sets.

IT Informatics

Jincheng Zhang

This paper introduces a novel self-adaptive quantum neural network (QNN) parameter adjustment algorithm. Traditional QNN parameter adjustment methods often rely on static adjustments, failing to effectively handle complex problems. Our algorithm dynamically adjusts the quantum neural network's parameters based on the input data, enabling automated and optimized training. We present a method that leverages a dynamic parameter adjustment strategy, improving the efficiency of quantum neural network training. The core mechanism centers around a feedback loop that continuously refines the network's parameters using the input data, leading to enhanced performance and adaptability. This work represents a significant advancement in QNN parameter optimization, offering a robust and automated approach to training.

G. Bonnell, G. Papini

Bu-Qing Chen, Xu-Feng Niu

Fernando M. de Paula Neto, Teresa B. Ludermir, Wilson Rosa de Oliveira

This paper reports the performance of a novel training algorithm for quantum neural networks (QNN) using a variation of the quantum search algorithm. The proposed algorithm trains a QNN exploring all possible weights with a sublinear cost. The training cost is theoretically O(√(N/t)), as a function of the quantity N of possible weights and t is the number of possible solutions. Initial experimental results demonstrate that the algorithm always converges to existing solutions, in addition to having the mean and maximum values, almost in total, lower than the expected maximum amount, as theoretically expected. The training algorithm is applied to classification problems.