I'm a PhD student at the Technion in the field of Geometric Deep learning supervised by Dr. Nadav Dym. I research and develop GNNs that process geometric data such as point clouds. I focus on theoretically justifying the GNN implementations I propose, along with attaining results on benchmark datasets. Papers I lead-authored were accepted to top AI venues such as AAAI and ICML. Open to collaborations on learning on point clouds and ML under symmetries.
Hordan, S., Amir, T., Dym, N. (2024) Weisfeiler Leman for Euclidean Equivariant Machine Learning. The Forty-first International Conference on Machine Learning.
Hordan, S., Amir, T., Gortler, S. J., Dym, N. (2024). Complete Neural Networks for Complete Euclidean Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 38(11), 12482-12490.
BSc. Mathematics (2017-2021)
Grade: 89
Relevant courses: Systems Programming (C++), Deep Learning
PhD Applied Mathematics (2022-2027 Expected)
Grade: 95
Direct Track PhD
Recipient of Technion's Faculty of Applied Math Excellence Scholarship