1 code implementation • 28 Nov 2022 • Dario Malchiodi, Davide Raimondi, Giacomo Fumagalli, Raffaele Giancarlo, Marco Frasca
Learned Bloom Filters, i. e., models induced from data via machine learning techniques and solving the approximate set membership problem, have recently been introduced with the aim of enhancing the performance of standard Bloom Filters, with special focus on space occupancy.
no code implementations • 13 Dec 2021 • Giacomo Fumagalli, Davide Raimondi, Raffaele Giancarlo, Dario Malchiodi, Marco Frasca
Bloom Filters are a fundamental and pervasive data structure.
1 code implementation • 28 Aug 2021 • Giosuè Cataldo Marinò, Alessandro Petrini, Dario Malchiodi, Marco Frasca
The state-of-the-art performance for several real-world problems is currently reached by convolutional neural networks (CNN).
no code implementations • 15 Jul 2020 • Giosuè Cataldo Marinò, Gregorio Ghidoli, Marco Frasca, Dario Malchiodi
Recent advances in deep learning have made available large, powerful convolutional neural networks (CNN) with state-of-the-art performance in several real-world applications.
no code implementations • 10 Apr 2019 • Marco Frasca, Giuliano Grossi, Giorgio Valentini
We show that by appropriately building a unique HN embedding all tasks, a more robust and effective classification model can be learned.
no code implementations • 18 May 2018 • Marco Frasca, Nicolò Cesa-Bianchi
Motivated by applications in protein function prediction, we consider a challenging supervised classification setting in which positive labels are scarce and there are no explicit negative labels.
no code implementations • 3 Nov 2016 • Marco Frasca, Nicolò Cesa Bianchi
Automated protein function prediction is a challenging problem with distinctive features, such as the hierarchical organization of protein functions and the scarcity of annotated proteins for most biological functions.