Saved in:
Bibliographic Details
Main Authors: Tognini, Paolo Alessandro Xavier, Banchi, Leonardo, De Palma, Giacomo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.14789
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909617852776448
author Tognini, Paolo Alessandro Xavier
Banchi, Leonardo
De Palma, Giacomo
author_facet Tognini, Paolo Alessandro Xavier
Banchi, Leonardo
De Palma, Giacomo
contents We propose a new quantum neural network for image classification, which is able to classify the parity of the MNIST dataset with full resolution with a test accuracy of up to 97.5% without any classical pre-processing or post-processing. Our architecture is based on a mixture of experts whose model function is the sum of the model functions of each expert. We encode the input with amplitude encoding, which allows us to encode full-resolution MNIST images with 10 qubits and to implement a convolution on the whole image with just a single one-qubit gate. Our training algorithm is based on training all the experts together, which significantly improves trainability with respect to training each expert independently. In fact, in the limit of infinitely many experts, our training algorithm can perfectly fit the training data. Our results demonstrate the potential of our quantum neural network to achieve high-accuracy image classification with minimal quantum resources, paving the way for more scalable and efficient quantum machine learning models.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14789
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Solving MNIST with a globally trained Mixture of Quantum Experts
Tognini, Paolo Alessandro Xavier
Banchi, Leonardo
De Palma, Giacomo
Quantum Physics
We propose a new quantum neural network for image classification, which is able to classify the parity of the MNIST dataset with full resolution with a test accuracy of up to 97.5% without any classical pre-processing or post-processing. Our architecture is based on a mixture of experts whose model function is the sum of the model functions of each expert. We encode the input with amplitude encoding, which allows us to encode full-resolution MNIST images with 10 qubits and to implement a convolution on the whole image with just a single one-qubit gate. Our training algorithm is based on training all the experts together, which significantly improves trainability with respect to training each expert independently. In fact, in the limit of infinitely many experts, our training algorithm can perfectly fit the training data. Our results demonstrate the potential of our quantum neural network to achieve high-accuracy image classification with minimal quantum resources, paving the way for more scalable and efficient quantum machine learning models.
title Solving MNIST with a globally trained Mixture of Quantum Experts
topic Quantum Physics
url https://arxiv.org/abs/2505.14789