Name: Antonio Macaluso
Type: User
Company: German Research Center for Artificial Intelligence
Bio: Senior Researcher in Quantum Artificial Intelligence
| PhD in Computer Science and Engineering
Twitter: macalcubo
Location: Saarbrücken, Germany
Blog: https://amacaluso.github.io/
Antonio Macaluso's Projects
Machine Learning and Deep Learning in Bioinformatics - Master's thesis repository
This project contains the code to perform a task of Particle identification (PID) in Astrophysics, comparing Deep Learning and Classical Machine Learning approaches. Data are provided by Agile team (http://agile.rm.iasf.cnr.it/) and the goal of the analysis is to provide a Statistical model which is able to distinguish gamma-ray photon for background particles.
This repository contains the code to reproduce the results in the paper Quantum Algorithm for Ensemble Learning
This repository contains the code to reproduce the results in the paper Quantum Ensemble for Classification. All the quantum implementations use the IBM qiskit package.
This repository contains the code to reproduce the results in the paper A Variational algorithm for Quantum Neural Networks, accepted in the International Conference on Computational Science 2020, Quantum Computing track.
This repository contains the code to reproduce the results in the paper Quantum Splines for Non-Linear Approximation, under publication for the ACM International Conference on Computing Frontiers 2020.
Questo è il repository ufficiale del corso di Quantum Computing di Deep Learning Italia Academy
Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing: we investigate the robustness of hashing methods based on variational autoencoders to the lack of supervision, focusing on two semi-supervised approaches currently in use. In addition, we propose a novel supervision approach in which the model uses its own predictions of the label distribution to implement the pairwise objective. Compared to the best baseline, this procedure yields similar performance in fully-supervised settings but improves significantly the results when labelled data is scarce.
This repository is intended to provide a slideshow of classification models, with a focus on the statistical properties of each approach. Specifically, a wide variety of both linear and non-linear methods are adopted and then compared, ranging from Linear Probability Model and Logistic Regression to Quadratic Discriminant Analysis and Generalised Additive Models.