arXiv subjects

Felipe Mahlow

Publications and source records attributed to Felipe Mahlow.

5 recordsLinked to original sources

arXiv2026

From Foundation ECG Models to NISQ Learners: Distilling ECGFounder into a VQC Student

Foundation models have recently improved electrocardiogram (ECG) representation learning, but their deployment can be limited by computational cost and latency constraints. In this work, we fine-tune ECGFounder as a high-capacity teacher for binary ECG classification on PTB-XL and the MIT-BIH Arrhythmia Database, and investigate whether knowledge distillation can transfer its predictive behavior to compact students. We evaluate two classical 1D students (ResNet-1D and a lightweight CNN-1D) and a quantum-ready pipeline that combines a convolutional autoencoder, which compresses 256-sample ECG windows into a low-dimensional latent representation, with a 6-qubit variational quantum circuit implemented in Qiskit and executed in a simulated backend. Across both datasets, the teacher provides the strongest overall performance, while distillation yields competitive students under a considerable reduction in trainable parameters. We further analyze the sensitivity of student performance to distillation settings, highlighting consistent accuracy--efficiency trade-offs when compressing a foundation ECG model into classical and quantum-ready learners under a unified evaluation protocol.

quant-ph↗

arXiv2025

Quantum Phases Classification Using Quantum Machine Learning with SHAP-Driven Feature Selection

In this study, we present an innovative methodology to classify quantum phases within the ANNNI (Axial Next-Nearest Neighbor Ising) model by combining Quantum Machine Learning (QML) techniques with the Shapley Additive Explanations (SHAP) algorithm for feature selection and interpretability. Our investigation focuses on two prominent QML algorithms: Quantum Support Vector Machines (QSVM) and Variational Quantum Classifiers (VQC). By leveraging SHAP, we systematically identify the most relevant features within the dataset, ensuring that only the most informative variables are utilized for training and testing. The results reveal that both QSVM and VQC exhibit exceptional predictive accuracy when limited to 5 or 6 key features, thereby enhancing performance and reducing computational overhead. This approach not only demonstrates the effectiveness of feature selection in improving classification outcomes but also offers insights into the interpretability of quantum classification tasks. The proposed framework exemplifies the potential of interdisciplinary solutions for addressing challenges in the classification of quantum systems, contributing to advancements in both machine learning and quantum physics.

quant-ph↗

arXiv2024

Illustrating Classic Brazilian Books using a Text-To-Image Diffusion Model

In recent years, Generative Artificial Intelligence (GenAI) has undergone a profound transformation in addressing intricate tasks involving diverse modalities such as textual, auditory, visual, and pictorial generation. Within this spectrum, text-to-image (TTI) models have emerged as a formidable approach to generating varied and aesthetically appealing compositions, spanning applications from artistic creation to realistic facial synthesis, and demonstrating significant advancements in computer vision, image processing, and multimodal tasks. The advent of Latent Diffusion Models (LDMs) signifies a paradigm shift in the domain of AI capabilities. This article delves into the feasibility of employing the Stable Diffusion LDM to illustrate literary works. For this exploration, seven classic Brazilian books have been selected as case studies. The objective is to ascertain the practicality of this endeavor and to evaluate the potential of Stable Diffusion in producing illustrations that augment and enrich the reader's experience. We will outline the beneficial aspects, such as the capacity to generate distinctive and contextually pertinent images, as well as the drawbacks, including any shortcomings in faithfully capturing the essence of intricate literary depictions. Through this study, we aim to provide a comprehensive assessment of the viability and efficacy of utilizing AI-generated illustrations in literary contexts, elucidating both the prospects and challenges encountered in this pioneering application of technology.

cs.AI↗

arXiv2023

Predicting the Onset of Quantum Synchronization Using Machine Learning

We have applied a machine learning algorithm to predict the emergence of environment-induced spontaneous synchronization between two qubits in an open system setting. In particular, we have considered three different models, encompassing global and local dissipation regimes, to describe the open system dynamics of the qubits. We have utilized the $k$-nearest neighbors algorithm to estimate the long time synchronization behavior of the qubits only using the early time expectation values of qubit observables in these three distinct models. Our findings clearly demonstrate the possibility of determining the occurrence of different synchronization phenomena with high precision even at the early stages of the dynamics using a machine learning-based approach. Moreover, we show the robustness of our approach against potential measurement errors in experiments by considering random errors in qubit expectation values. We believe that the presented results can prove to be useful in experimental studies on the determination of quantum synchronization.

quant-ph↗

arXiv2021

Model-Independent Quantum Phases Classifier

Machine learning has revolutionized many fields of science and technology. Through the $k$-Nearest Neighbors algorithm, we develop a model-independent classifier, where the algorithm can classify phases of a model to which it has never had access. For this, we study three distinct spin-$1$ models with some common phases: the XXZ chains with uniaxial single-ion-type anisotropy, the bound alternating XXZ chains, and the bilinear biquadratic chain. We show that, with high probability, algorithms trained with two of these models can determine common phases with the third. It is the first step toward a universal classifier, where an algorithm is able to detect any phase with no knowledge about the Hamiltonian, only knowing partial information about the quantum state.

quant-ph↗