Scholar
Alejandro García-Castellanos
Google Scholar ID: dzdhlJwAAAAJ
Ph.D. student, University of Amsterdam
Citations & Impact
Citations
9
H-index
2
i10-index
0
Publications
7
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Published papers: Equivariant Eikonal Neural Networks, HyperSteiner: Computing Heuristic Hyperbolic Steiner Minimal Trees, Relative Representations: Topological and Geometric Perspectives, Learning symmetries via weight-sharing with doubly stochastic tensors; Participated in multiple academic conferences and presented research findings.
Research Experience
- PhD Candidate, AMLab @ UvA, February 2024 – Present, Amsterdam, Netherlands, under the supervision of Erik Bekkers (University of Amsterdam) and co-supervision of Daniël Pelt (University of Leiden), developing techniques for collaborative human-computer image annotation of training sets for deep learning tasks; Research Engineer, Division of Robotics, Perception and Learning @ KTH, March 2023 – February 2024, Stockholm, Sweden, projects under the supervision of Danica Kragic, delved into Geometric Deep Learning and Lie groups while working on a project that involved devising path-finding algorithms on learned equivariant representations through class-pose decomposition, also explored Manifold Learning techniques.
Education
- MSc in Machine Learning, 2023, KTH Royal Institute of Technology; BSc in Mathematics and Computer Science, 2021, Universidad Politécnica de Madrid
Background
- PhD candidate at the University of Amsterdam, focusing on applying topology, algebra, and geometry in machine learning. Research interests include Representation Learning, Geometric Deep Learning, Topological Machine Learning, and Non-Euclidean Geometry.
