analiza aiqbench
This bachelor's thesis proposes a binary quantum classifier using the Qibo framework to distinguish between handwritten digits and high-energy collision data, including scenarios with proton-proton pile-up. The study evaluates the model's performance against classical convolutional neural networks by analyzing ROC curves and accuracy metrics across varying circuit depths and dataset sizes. Ultimately, the work provides a baseline assessment of the current capabilities and limitations of quantum circuits for binary classification tasks in quantum machine learning.
Towards the implementation of a quantum classifier
arXiv:2606.10150v1 Announce Type: new Abstract: In this work, we investigate the use of a quantum circuit as a binary classification model in the context of quantum machine learning. We call this model, binary quantum classifier. First, we describe fundamental concepts of quantum computing and introduce the computational tool used: Qibo, an open-source framework for efficient quantum simulations and quantum hardware control. Then, we describe how to design a binary quantum classifier for the classification of images and small arrays of variables by showing how to input data in the circuit, defining a quantum circuit model Ansatz with trainable parameters and a loss function, and implementing multiple minimizers. We test our quantum classifier with two data sets. The first one is the MNIST data set which is composed of handwritten digits (reduced to only handwritten zeros and handwritten ones for binary classification). We study the behavior of different minimizers by increasing the number of layers of the Ansatz. The second data set represents two different high energy collisions that can occur at colliders such as LHC (CERN). Due to in-time proton-proton interactions known as pile-up, we distinguish two different data sets: "without pile-up" and "with pile-up". These collisions can be represented by images of size 32x32 or by six high-level variables that we call features. By increasing the size of the training data set and the number of layers of the Ansatz, we search for the best minimizer. Splitting the data set in training set and test set, we compute: ROC curve, AUC score, confusion matrices and test set accuracy. For "with pile-up" images, we compare the results obtained with the quantum classifier with a small convolutional neural network. We conclude that is possible to build a binary quantum classifier with a quantum circuit and we highlight its performances and limitations in comparison with classical technologies.
Abstract:In this work, we investigate the use of a quantum circuit as a binary classification model in the context of quantum machine learning. We call this model, binary quantum classifier. First, we describe fundamental concepts of quantum computing and introduce the computational tool used: Qibo, an open-source framework for efficient quantum simulations and quantum hardware control. Then, we describe how to design a binary quantum classifier for the classification of images and small arrays of variables by showing how to input data in the circuit, defining a quantum circuit model Ansatz with trainable parameters and a loss function, and implementing multiple minimizers. We test our quantum classifier with two data sets. The first one is the MNIST data set which is composed of handwritten digits (reduced to only handwritten zeros and handwritten ones for binary classification). We study the behavior of different minimizers by increasing the number of layers of the Ansatz. The second data set represents two different high energy collisions that can occur at colliders such as LHC (CERN). Due to in-time proton-proton interactions known as pile-up, we distinguish two different data sets: "without pile-up" and "with pile-up". These collisions can be represented by images of size 32x32 or by six high-level variables that we call features. By increasing the size of the training data set and the number of layers of the Ansatz, we search for the best minimizer. Splitting the data set in training set and test set, we compute: ROC curve, AUC score, confusion matrices and test set accuracy. For "with pile-up" images, we compare the results obtained with the quantum classifier with a small convolutional neural network. We conclude that is possible to build a binary quantum classifier with a quantum circuit and we highlight its performances and limitations in comparison with classical technologies.
Bachelor's Thesis in Physics, Lorenzo Confalonieri, Università degli Studi di Milano (July 2021). 55 pages, 28 figures. Code implementations utilize the Qibo framework
Quantum Physics (quant-ph); High Energy Physics - Experiment (hep-ex); Computational Physics (physics.comp-ph)
arXiv:2606.10150 [quant-ph]
(or arXiv:2606.10150v1 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2606.10150 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 350 cuvinte
Subiecte conexe
Towards the implementation of a quantum classifier
arXiv · 11 iun. 2026
Logic Gate Networks and Lookup Table Networks as Lightweight Hardware Classifiers for Inter-patient ECG Arrhythmia Classification
arXiv · 30 sept. 2026
JevForest: Path Voting for Budgeted Feature Acquisition
arXiv · 9 oct. 2026
RF Fingerprinting of DSP Implementations using Machine Learning: An Over-the-Air Case Study
arXiv · 14 oct. 2026