- Semester B 2023: MTH767P Neural Networks and Deep Learning
- Semester A 2022: MTH765P Storing, Manipulating and Visualising Data
- Semester B 2022: MTH767P Neural Networks and Deep Learning
- Semester A 2021: MTH793P Advanced Machine Learning
In my research I am interested in using methods from algebra, geometry and topology to study data. I am currently particularly interested in advancing our understanding of weather regimes using methods from topology, as well as developing algebraic and topological methods to model higher-order relationships in social systems.
Examples of research funding:
- Royal Society Research Grant (£16,959.60) 02.2022 - 02.2023
My research is interdisciplinary, and the order of authors in different publications follows conventions dictated by different disciplines.
A topological perspective on weather regimes, K. Strommen, M. Chantry, J. Dorrington, NO, 2021, to appear in Climate Dynamics
On the effectiveness of persistent homology, R. Turkeš, G. Montúfar, NO, 2022
Amplitudes on abelian categories, B. Giunti, J. Nolan, NO, L. Waas, 2021
Stratifying multiparameter persistent homology, H. Harrington, NO, H. Schenck, U. Tillmann), SIAM Journal on Applied Algebraic Geometry, 3(3):439-471 (2019)
A roadmap for the computation of persistent homology, NO, M. Porter, U. Tillmann, P. Grindrod, H. Harrington, EPJ Data Science, 2017, 6:17 (2017)
Alpha magnitude, M. O’Malley, S. Kalisnik, NO, 2022
Magnitude meets persistence. Homology theories for filtered simplicial sets, NO, Homology, Homotopy and Applications, 24(2), 2022, pp.401-423
A unififed framework for equivalences in social networks, NO, M. A. Porter, 2020
Geometric deep learning
Weisfeiler and Lehman Go Cellular: CW Networks, C. Bodnar, F. Frasca, NO, Y. G. Wang, P. Liò, G. Montúfar, M. Bronstein, Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks, C. Bodnar, F. Frasca, Y. G. Wang, G. Montufar, NO, P. Lio, M. Bronstein, Proceedings of the 38th International Conference on Machine Learning (ICML 2021)
Can neural networks learn persistent homology features?, G. Montufar, Y. G. Wang, NO, Topological Data Analysis and Beyond Workshop, at the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada
Operads and phylogenetic trees, J. Baez, NO, Theory and Applications of Categories, 33(40):1397-1453 (2017).