Teaching

University of Iceland
20/10/2020
Deep Learning driven by Big Data

Invited lecture on ''Deep Learning driven by Big Data'' in the Cloud Computing and Big Data course at the University of Iceland. The lecture first introduces to the limitations of a linear perceptron model and how Artificial Neural Networks (ANNs) can solve non-linearly separable data sets. Then, it explains how Convolutional Neural Networks (CNNs) can solve image recognition tasks. Finally it is demonstrates how to tune the parameters of the networks with the backpropagation algorithm.

Learn more
University of Bonn
WS 2020-2021
Parallel and Scalable Machine Learning for Remote Sensing Big Data

Recent advances in remote sensors with higher spectral, spatial, and temporal resolutions have significantly increased data volumes, which pose a challenge to process and analyse the resulting massive data in a timely fashion to support practical applications. Meanwhile, the development of computationally demanding Machine Learning (ML) and Deep Learning (DL) techniques (e.g., deep neural networks with massive amounts of tunable parameters) demand for parallel algorithms with high scalability performance. Therefore, data intensive computing approaches have become indispensable tools to deal with the challenges posed by applications from geoscience and remote sensing. In recent years, high-performance and distributed computing have been rapidly advanced in terms of hardware architectures and software. For instance, the popular graphics processing unit (GPU) has evolved into a highly parallel many-core processor with tremendous computing power and high memory bandwidth. Moreover, recent High Performance Computing (HPC) architectures and parallel programming have been influenced by the rapid advancement of DL and hardware accelerators as modern GPUs. This and more in my course on Scalable Machine Learning for Remote Sensing Big Data.

Learn more
IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
26-27/09/2020
Scalable Machine Learning with High Performance and Cloud Computing

Deep Learning is emerging as the leading AI technique owing to the current convergence of scalable computing capability (i.e., HCP and Cloud computing), easy access to large volumes of data, and the emergence of new algorithms enabling robust training of large-scale deep neural networks. The tutorial aims at providing a complete overview for an audience that is not familiar with these topics.

Learn more
Jülich Supercomputing Centre
February 2020
PRACE Tutorial Parallel and Scalable Machine Learning

The course starts by teaching the basics of machine learning and data mining algorithms to understand the foundations of ''learning from data''. Then the course points to key challenges in analyzing large quantities of data sets in order to motivate the use of parallel and scalable machine learning algorithms.

Learn more
TU Berlin
May 2020
Image Filtering with Mathematical Morphology Operators

Mathematical Morphology is a well established framework for image filtering. Fundamental mathematical morphology operators, such as Erosion and Dilation (and their combinations: opening and closing) examine the geometrical structures in the image by matching them to small patterns, called Structuring Elements.

Learn more
University of Bonn
WS 2019-2020
Parallel and Scalable Machine Learning for Remote Sensing Big Data

This course exposes the student to the physical principles underlying satellite observations of Earth by passive sensors, as well as parallel and scalable machine (deep) learning algorithms for the automatic classification of land cover classes from remote sensing images.

Learn more