Personal Webpage of Francesco Ballerin

PhD fellow at the University of Bergen

I am currently on the job market. My PhD is expected to conclude at the end of September 2026. If you have an open position for which I may be a suitable candidate, please do not hesitate to contact me at francesco@ballerin.it.

Work Experience

PhD Candidate with Teaching Duties

University of Bergen
2022 - Current
  • Research topics: Geometric Deep Learning, Differential Geometry, Computer Vision. More details available in the Research tab.
  • Teaching duties: Real Analysis, Fourier Analysis, Measure and Integration Theory, Stochastic Processes.

Junior Research Assistant

FBK — Fondazione Bruno Kessler
2017 - 2019
  • Predictive models for agricultural yields, quality estimation, and pesticide management from meteorological data and spectrophotometry analysis.
  • Development of LoRa-Network solutions for machine learning in an IoT environment.

Education

PhD in Mathematics

University of Bergen
2022 - Current
Thesis: Geometrical Methods for Data Analysis

Research in geometric deep learning and equivariant methods for data on manifolds and curved spaces. Covers topics including equivariant neural networks on the sphere, PDE-based data analysis, and sub-Riemannian geometry. More details are available in the Research tab.


Master's Degree in Mathematical Analysis

University of Bergen
2020 - 2022
Avg. grade: A  |  Thesis: Sub-Riemannian geometry and its applications to image processing

After an introduction on sub-Riemannian geometry, focusing on the examples of the Lie group \(SE(2)\) and the projective tangent bundle \(PT\mathbb{R}^2\), applications to the field of image processing are discussed. In particular we study a model of geometry of vision for image restoration due to Petitot, Citti and Sarti and further developments by Boscain, Duplaix, Gauthier and Rossi on hypoelliptic operators. New tools and techniques based on such work are developed and discussed.


Bachelor's Degree in Mathematics

University of Trento
2017 - 2020
Grade: 107/110  |  Thesis: Active Contour Models for Image Segmentation and Motion Tracking

Traditional image segmentation methods based on global and local thresholds and the detection of intensity discontinuities have been widely used for numerous applications, but they intrinsically have multiple limitations. Two PDE-based active contours approaches, inspired by the fundamental snake equation presented by Kass, Witkin and Terzopoulos, are discussed. An implementation is then produced, as well as an extension of the algorithm to realize active tracking on video files.


Schools & Training

NORA Summer School

NORA AI
June 2024

School covering advanced topics in machine learning with a focus on geometric deep learning, symmetry-aware models, and their applications to structured data. Included both theoretical foundations and hands-on work with modern ML methods.


Geilo Winter School

SINTEF
January 2024

School focusing on graph-based data analysis and machine learning. Covered spectral graph theory, graph signal processing, and graph neural networks.

Skills

Programming

Python, C++, C, Java, Kotlin, JavaScript, PHP, MATLAB, MySQL

Frameworks & Libraries

PyTorch, PyTorch Geometric, NetworkX, Pandas

Tools

Git, Jupyter, LaTeX, HTML, CSS

Languages
Italian Mother tongue
English C2
Norwegian B2
German A2

Certificates, Awards & Grants

2023 Meltzer Universitetsstiftelse — Research grant
2022 Meltzer Universitetsstiftelse — Research grant
2018 1st place — Vertical Innovation Hackathon, Bolzano
2017 Best Software Programming — RoboCup Junior World Championship, Nagoya