ROMSOC Training Course "Introduction to Deep Learning"
We are happy to announce the upcoming ROMSOC training course "Introduction to Deep Learning" in the framework of the research project ROMSOC - Reduced Order Modelling, Simulation and Optimization of Coupled Systems funded by European Union's Horizon 2020 programme in the Marie Sklodowska-Curie Action (MSCA).
It will take place at the Center for Industrial Mathematics, University of Bremen, September 23-27, 2019.
The course provides an introduction to machine learning and in particular neural networks for practical deep learning applications, as well as an overview of the underlying mathematical tools and theory. A major focus will be on applications in image processing and computer vision.
The course will cover several subjects including linear and multilayer networks, back-propagation, loss functions, convolutional and pooling layers, initialization schemes, batch normalization, common classification and segmentation tasks and their respective datasets, and popular neural networks models.
Hands-on sessions with an introduction to PyTorch are included in the exercise sections of the training programme.
Lecturers
Niv Haim (Weizmann Institute of Science and SagivTech Ltd., Israel)
Prof. Dr. Dr. h.c. Peter Maass (University of Bremen)
Daniel Otero Baguer (University of Bremen)
Niv Haim is a Phd student at Weizmann Institute of Science in Yaron Lipman's lab, Israel. Haim's research revolves around combining ideas between machine learning and computational geometry, such as using deep learning on surfaces, point clouds, graphs etc. or borrowing geometrical ideas to solve learning tasks. Niv Haim did his masters in theoretical astrophysics, and before that he completed his undergrad in computer science and physics at the Technion. Niv Haim also plays the violin and is happy to chat about music, history and geography.
Organization committee
Dr. Lena Hauberg-Lotte (University of Bremen, Germany)
Dörte Mindermann (University of Bremen, Germany)
José Carlos Gutiérrez Pérez (University of Bremen, Germany)
Dr. Chen Sagiv (SagivTech Ltd., Israel)
Christian Etmann (University of Bremen, Germany)
Jens Behrmann (University of Bremen, Germany)
Acknowledgments
We gratefully acknowledge the support of this Training Course by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 765374. Thanks to Dr. Matthias Knauer for his help in setting up this website.
It will take place at the Center for Industrial Mathematics, University of Bremen, September 23-27, 2019.
The course provides an introduction to machine learning and in particular neural networks for practical deep learning applications, as well as an overview of the underlying mathematical tools and theory. A major focus will be on applications in image processing and computer vision.
The course will cover several subjects including linear and multilayer networks, back-propagation, loss functions, convolutional and pooling layers, initialization schemes, batch normalization, common classification and segmentation tasks and their respective datasets, and popular neural networks models.
Hands-on sessions with an introduction to PyTorch are included in the exercise sections of the training programme.
Lecturers
Niv Haim (Weizmann Institute of Science and SagivTech Ltd., Israel)
Prof. Dr. Dr. h.c. Peter Maass (University of Bremen)
Daniel Otero Baguer (University of Bremen)
Niv Haim is a Phd student at Weizmann Institute of Science in Yaron Lipman's lab, Israel. Haim's research revolves around combining ideas between machine learning and computational geometry, such as using deep learning on surfaces, point clouds, graphs etc. or borrowing geometrical ideas to solve learning tasks. Niv Haim did his masters in theoretical astrophysics, and before that he completed his undergrad in computer science and physics at the Technion. Niv Haim also plays the violin and is happy to chat about music, history and geography.
Organization committee
Dr. Lena Hauberg-Lotte (University of Bremen, Germany)
Dörte Mindermann (University of Bremen, Germany)
José Carlos Gutiérrez Pérez (University of Bremen, Germany)
Dr. Chen Sagiv (SagivTech Ltd., Israel)
Christian Etmann (University of Bremen, Germany)
Jens Behrmann (University of Bremen, Germany)
Acknowledgments
We gratefully acknowledge the support of this Training Course by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 765374. Thanks to Dr. Matthias Knauer for his help in setting up this website.
