Deep Learning using a Convolutional Neural Network

This course part focuses on a recent machine learning method known as deep learning that emerged as a promising disruptive approach, allowing knowledge discovery from large datasets in an unprecedented effectiveness and efficiency. It is particularly relevant in research areas, which are not accessible through modelling and simulation often performed in HPC. Traditional learning, which was introduced in the 1950s and became a data-driven paradigm in the 90s, is usually based on an iterative process of feature engineering, learning, and modelling. Although successful on many tasks, the resulting models are often hard to transfer to other datasets and research areas. This course provides an introduction into deep learning and its inherent ability to derive optimal and often quite generic problem representations from the data (aka ‘feature learning’). Concrete architectures such as Convolutional Neural Networks (CNNs) will be applied to real datasets of applications using known deep learning frameworks such as Tensorflow, Keras, or Torch. As the learning process with CNNs is extremely computational-intensive the course will cover aspects of how parallel computing can be leveraged in order to speed-up the learning process using general purpose computing on graphics processing units (GPGPUs). Hands-on exercises allow the participants to immediately turn the newly acquired skills into practice. After this course participants will have a general understanding for which problems CNN learning architectures are useful and how parallel and scalable computing is facilitating the learning process when facing big datasets. About the lecturer: Prof. Dr. – Ing. Morris Riedel received his PhD from the Karlsruhe Institute of Technology (KIT) and he is the head of the ‘high productivity data processing’ research group of the Juelich Supercomputing Centre (JSC) in Germany. As an adjunct associated professor at the School of Natural Sciences and Engineering of the University of Iceland he teaches ‘High Performance Computing’, ‘Cloud Computing and Big Data’, as well as ‘Statistical Data Mining’ and all of these courses are on the intersection of parallel computing and machine learning. He has given tutorials like the course above at numerous occasions like at the Barcelona Supercomputing Centre, Smart Data Innovation Conference, or Prace Spring School in Cyprus. His research interests are parallel and scalable machine learning and data science. (More info at http://www.morrisriedel.de )

Scientific topics: Machine learning

Resource type: Video

Target audience: PhD students, Post Docs

Difficulty level: Intermediate

Authors: Morris Riedel

Deep Learning using a Convolutional Neural Network https://tess.elixir-europe.org/materials/deep-learning-using-a-convolutional-neural-network This course part focuses on a recent machine learning method known as deep learning that emerged as a promising disruptive approach, allowing knowledge discovery from large datasets in an unprecedented effectiveness and efficiency. It is particularly relevant in research areas, which are not accessible through modelling and simulation often performed in HPC. Traditional learning, which was introduced in the 1950s and became a data-driven paradigm in the 90s, is usually based on an iterative process of feature engineering, learning, and modelling. Although successful on many tasks, the resulting models are often hard to transfer to other datasets and research areas. Machine learning PhD students Post Docs
Ajax loader