About Aku-Jaakko Alexis Kammonen Aku-Jaakko Alexis Kammonen Research Scientist, Stochastic Numerics Research Group numerical methods machine learning 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). Articles Related News November 2023 Research visit to RWTH Aachen by Aku Kammonen and Erik von Schwerin 1 min read · Tue, Nov 7 2023 News Aku Kammonen and Erik von Schwerin visited the MATH4UQ chair at RWTH Aachen. During the visit to the chair, they worked on an ongoing collaboration with Dr. Anamika Pandey. This research builds on previous work by Kammonen and co-authors, published in the paper Adaptive random Fourier features with Metropolis sampling. They also had the opportunity to discuss research with several students at the chair. Aku and Erik would like to thank all of their hosts for making it a memorable and productive visit. September 2023 Erik von Schwerin and Aku Kammonen visited RWTH Aachen University in last week of September 1 min read · Wed, Sep 20 2023 News For two weeks in August and September 2023, Aku Kammonen and Erik von Schwerin visited the MATH4UQ chair at RWTH Aachen. During the visit to the chair, they enjoyed informal research discussions with all present group members. They mainly focused on an ongoing collaboration with Dr. Anamika Pandey. This research builds on previous work by Kammonen and co-authors, published in the paper Adaptive random Fourier features with Metropolis sampling. Aku and Erik would like to thank their hosts for their kind hospitality August 2023 Post-Doc Aku Jakko Kammonen participation at UNCECOMP 2023, 5th International Conference on Uncertainty Quantification in Computational Science and Engineering 1 min read · Tue, Aug 1 2023 News A postdoctoral fellow of our group Dr. Aku Jaakko Kammonen participated in the recently concluded UNCECOMP 2023, 5th International Conference on Uncertainty Quantification in Computational Science and Engineering and presented a talk on Adaptive random Fourier features based on Metropolis sampling . The Conference held at Athens, Greece, between June 12-14, 2023. Abstract : The supervised learning problem to approximate a function f by a neural network approximation with one hidden layer of width K is studied as a random Fourier features algorithm. Here the mean square loss problem can be Post-Doc Aku Jakko Kammonen participation at Siam Conference on Computational Science and Engineering (CSE23) 1 min read · Tue, Aug 1 2023 News A postdoctoral fellow of our group Dr. Aku Jaakko Kammonen participated in the recently concluded Conference on Computational Science and Engineering (CSE23) and presented a talk on Adaptive random Fourier features based on Metropolis sampling. The Conference held at Amsterdam, Netherlands, between February 26 - March 3, 2023. Abstract: The supervised learning problem to approximate a function $f:\mathbb R^d\to\mathbb R$ by a neural network approximation $\mathbb{R}^d\ni x\mapsto\sum_{k=1}^K\hat\beta_k e^{{\mathrm{i}}\omega_k\cdot x}$ with one hidden layer is studied as a random Fourier October 2022 Article published in IMA Journal of Numerical Analysis 1 min read · Mon, Oct 24 2022 News residual network deep random feature networks supervised learning layer- by-layer algorithm In September 2022, the IMA Journal of Numerical Analysis published the article Smaller generalization error derived for a deep residual neural network compared with shallow networks, by Aku Kammonen (KAUST), Jonas Kiessling (KTH Royal Institute of Technology), Petr Plecháč (University of Delaware), Mattias Sandberg (KTH Royal Institute of Technology), Anders Szepessy (KTH Royal Institute of Technology), and Raul Tempone (KAUST). Abstract: Estimates of the generalization error are proved for a residual neural network with L random Fourier features layers. An optimal distribution for the
Research visit to RWTH Aachen by Aku Kammonen and Erik von Schwerin 1 min read · Tue, Nov 7 2023 News Aku Kammonen and Erik von Schwerin visited the MATH4UQ chair at RWTH Aachen. During the visit to the chair, they worked on an ongoing collaboration with Dr. Anamika Pandey. This research builds on previous work by Kammonen and co-authors, published in the paper Adaptive random Fourier features with Metropolis sampling. They also had the opportunity to discuss research with several students at the chair. Aku and Erik would like to thank all of their hosts for making it a memorable and productive visit.
Erik von Schwerin and Aku Kammonen visited RWTH Aachen University in last week of September 1 min read · Wed, Sep 20 2023 News For two weeks in August and September 2023, Aku Kammonen and Erik von Schwerin visited the MATH4UQ chair at RWTH Aachen. During the visit to the chair, they enjoyed informal research discussions with all present group members. They mainly focused on an ongoing collaboration with Dr. Anamika Pandey. This research builds on previous work by Kammonen and co-authors, published in the paper Adaptive random Fourier features with Metropolis sampling. Aku and Erik would like to thank their hosts for their kind hospitality
Post-Doc Aku Jakko Kammonen participation at UNCECOMP 2023, 5th International Conference on Uncertainty Quantification in Computational Science and Engineering 1 min read · Tue, Aug 1 2023 News A postdoctoral fellow of our group Dr. Aku Jaakko Kammonen participated in the recently concluded UNCECOMP 2023, 5th International Conference on Uncertainty Quantification in Computational Science and Engineering and presented a talk on Adaptive random Fourier features based on Metropolis sampling . The Conference held at Athens, Greece, between June 12-14, 2023. Abstract : The supervised learning problem to approximate a function f by a neural network approximation with one hidden layer of width K is studied as a random Fourier features algorithm. Here the mean square loss problem can be
Post-Doc Aku Jakko Kammonen participation at Siam Conference on Computational Science and Engineering (CSE23) 1 min read · Tue, Aug 1 2023 News A postdoctoral fellow of our group Dr. Aku Jaakko Kammonen participated in the recently concluded Conference on Computational Science and Engineering (CSE23) and presented a talk on Adaptive random Fourier features based on Metropolis sampling. The Conference held at Amsterdam, Netherlands, between February 26 - March 3, 2023. Abstract: The supervised learning problem to approximate a function $f:\mathbb R^d\to\mathbb R$ by a neural network approximation $\mathbb{R}^d\ni x\mapsto\sum_{k=1}^K\hat\beta_k e^{{\mathrm{i}}\omega_k\cdot x}$ with one hidden layer is studied as a random Fourier
Article published in IMA Journal of Numerical Analysis 1 min read · Mon, Oct 24 2022 News residual network deep random feature networks supervised learning layer- by-layer algorithm In September 2022, the IMA Journal of Numerical Analysis published the article Smaller generalization error derived for a deep residual neural network compared with shallow networks, by Aku Kammonen (KAUST), Jonas Kiessling (KTH Royal Institute of Technology), Petr Plecháč (University of Delaware), Mattias Sandberg (KTH Royal Institute of Technology), Anders Szepessy (KTH Royal Institute of Technology), and Raul Tempone (KAUST). Abstract: Estimates of the generalization error are proved for a residual neural network with L random Fourier features layers. An optimal distribution for the
Engage ORCID ShareClipboard Related Sites Stochastic Numerics Research Group (STOCHNUM) Applied Mathematics and Computational Science (AMCS) Related Content Articles 5 Related Links Aku Kammonen's publication list per year ResearchGate Profile
