
Aku Jaakko Alexis Kammonen
Aku Jaakko Alexis Kammonen is a Research Scientist at Stochastic Numerics Research Group under the supervision of Professor Raul F. Tempone at King Abdullah University of Science and Technology (KAUST).
Biography
- Ph.D. Applied and Computational Mathematics specialized in numerical analysis, Royal Institute of Technology (KTH), Sweden, 2021
- M.Sc. in Engineering, Microelectronics, International track, Japanese, Sweden, 2014
Research Interests
Aku's research interests include Machine Learning, Neural Networks, Random Features, Spectral Bias, Adversarial Attacks, PINNs, and Numerical Analysis.
About
Aku Jaakko Alexis Kammonen is a Research Scientist at Stochastic Numerics Research Group under the supervision of Professor Raul F. Tempone at King Abdullah University of Science and Technology (KAUST).
Research Interests
Aku's research interests include Machine Learning, Neural Networks, Random Features, Spectral Bias, Adversarial Attacks, PINNs, and Numerical Analysis.
Publications
- A. Kammonen, A. Pandey, E. von Schwerin, and R. Tempone. Adaptive random Fourier features training stabilized by resampling with applications in image regression. Foundations of Data Science, (2025).
- A. Kammonen, L. Liang, A. Pandey, and R. Tempone (2024, March 19–23). Comparing Spectral Bias and Robustness For Two-Layer Neural Networks: SGD vs Adaptive Random Fourier Features [Poster presentation], International Conference on Scientific Computing and Machine Learning 2024, Kyoto, Japan
- A. Kammonen, J. Kiessling, P. Plecháč, M. Sandberg, A. Szepessy, R. Tempone, Smaller generalization error derived for a deep residual neural network compared with shallow networks, IMA Journal of Numerical Analysis, Volume 43, Issue 5, September 2023, Pages 2585–2632
- A. Kammonen, J. Kiessling, P. Plecháč, M. Sandberg, A. Szepessy, Adaptive random Fourier features with Metropolis sampling, Foundations of Data Science, 2, 3, 309, 2020
- A. Kammonen, P. Plecháč, M. Sandberg, and A. Szepessy, (n.d.). Computational Algorithms For Canonical Ensemble Ob‑
servables. Published as part of PhD Thesis: Numerical algorithms for high dimensional integration with application to
machine learning and molecular dynamics (2020) - A. Kammonen, P. Plecháč, M. Sandberg, A. Szepessy, Canonical Quantum Observables for Molecular Systems Approximated by Ab Initio Molecular Dynamics, Ann. Henri Poincaré 19, 2727–2781, 2018
- A. Kammonen, On a one-phase quasi-static Stefan problem for planar polygonal crystals grown from vapor in a bounded container, Advances in Mathematical Sciences and Applications Vol. 24, No.2 (2014), pp.317–331
Preprints
- X. Huang, A. Kammonen, A. Pandey, M. Sandberg, E. von Schwerin, A. Szepessy, and R. Tempone. Convergence for adaptive
resampling of random Fourier features. arXiv, arXiv:2509.03151, (2025) - O. Douglas, A. Kammonen, A. Pandey, and R. Tempone. An Adaptive Random Fourier Features approach Applied to Learning
Stochastic Differential Equations. arXiv, arXiv:2507.15442, (2025)
Education Profile
- Ph.D. Applied and Computational Mathematics specialized in numerical analysis, Royal Institute of Technology (KTH), Sweden, 2021
- M.Sc. in Engineering, Microelectronics, International track, Japanese, Sweden, 2014
Qualifications
Education
- Doctor of Philosophy (Ph.D.)
- Applied and Numerical Mathematics, KTH, Royal Institute of Technology, Sweden, 2021
- Master of Science (M.S.)
- Microelectronics Science and Engineering, KTH, Royal Institute of Engineering, Sweden, 2014
Licenses and Certifications
- Harvard Bok Higher Education Teaching Certificate, Harvard, Mon, May 13 2024
- JLPT N2, Japanese‑Language Proficiency Test Certificate, Japan Educationional Exchanges and Services jointly with The Japan Foundation, Sun, Dec 1 2024
- English
- Full professional proficiency
- Swedish
- Native or bilingual proficiency
- Finnish
- Professional working proficiency
- Japanese
- Limited working proficiency