The 18th Geilo Winter School in eScience was held Sunday January 21st to Friday January 26th 2018 in Geilo, Norway.

The 2018 edition was an exciting new school on the topic of Practical use of Artificial Intelligence. Techniques within artificial intelligence are now able to extract knowledge from vast amounts of data on level we have not seen before, and AI has been a game changer for a range of application areas in recent years. This winter school will focus on the practical aspects of artificial intelligence and equip participants with the skills required to run machine learning tasks on their own data targeting their problems.

Part of the school will be a tutorial on using artificial intelligence techniques, with a large number of hands-on exercises for participants to fully grasp the topic. The aim is that the school becomes an interactive workshop with a high level of participant involvement. During the course of the winter school, you will learn different techniques, which libraries that implement these, and try them out for yourself. Participants are encouraged to prepare their own data and problems that they want to solve during the winter school. 

 Topics

The winter school will focus on practical use of artificial intelligence techniques, and cover tools and techniques such as artificial neural networks, deep learning, tensorflow, practical iartificial intelligence, machine learning, regression, concurrent neural networks, regression, scikit-learn. The tools and techniques area applicable to a wide range of problems, and examples on data from climatology, the automotive industry, image processing, etc. 

Daily Program

The winter school starts on Sunday afternoon with an introductory lecture, and continues until Friday after lunch. Each day starts with a morning session, a long mid-day break (well spent skiing and socializing), and two afternoon lectures. Participants should bring their own laptops to the school. 

The 2018 winter school flyer can be downloaded as a pdf here.

Andres Masegosa Arredondo Dr. Andres Masegosa has a Ph.D. in computer science from Universidad de Granada, Spain, and has been working on the AMISDT EU funded project (http://project.amidsttoolbox.com) for analyzing massive data streams with probabilistic graphical models. He is currently working as Principal Investigator in the project "INFER.java: A probablistic programming language for developing machine learning applications on big data" at the Universidad de Almeria.
Topics: The AMIDST toolbox, http://www.amidsttoolbox.com/
Linkedin

Eivind Fonn Dr. Eivind Fonn has a PhD from ETH Zurich and is a research scientist at SINTEF Digital. He works with applied mathematics, reduced order modeling, machine learning and artificial intelligence.
Topics: Machine learning and practical artificial intelligence
Linkedin

Anne C. Elster Professor Anne C. Elster is the founder and leader of the NTNU HPC-lab with a focus on GPU and high performance computing. She is currently involved in the CLOUDLIGHTNING project funded by the European Union, where she has been involved in the use of artificial intelligence and heterogeneous resources for HPC.
Topics: Using artificial intelligence to develop HPC
Webpage

Adil Rasheed Dr. Adil Rasheed is a senior scientist at SINTEF Digital and an associate professor at NTNU. He is the research manager for the Computational Science and Engineering group, and has a key role in the Big-Learning initiative within SINTEF.
Topics: Tutorial on machine learning and practical artificial intelligence
Webpage

Kjetil André Johannessen Dr. Kjetil Andre Johannessen is a researcher at SINTEF Digital and a postdoc at NTNU, and has been working with isogeometry, spline technologies, artificial intelligence, machine learning.
Topics: Tutorial on machine learning and practical artificial intelligence
Linkedin

Ole Christian Lingjærde Professor Ole Christian Lingjærde is affiliated with the research group focusing on Biomedical Informatics (BMI) at the Department of Informatics at the University of Oslo. He is also head of the Biostatistics and Bioinformatics group at the KG Jebsen Centre for Breast Cancer Research.
Topics: Regularization techniques for many covariates in regression and classification
Webpage

Mandar Tabib Dr. Mandar Tabib is a research scientist at SINTEF Digital where he works with fluid dynamics, machine learning and artificial intelligence within wind energy, transport safety, biomedicine, chemical engineering, reactive multi-phase flow, and aviation runway safety.
Topics: Tutorial on machine learning and practical artificial intelligence
Linkedin

Malik Khan Dr. Malik M. Khan is a research scientist at NTNU, where he works on the EU project Cloudlightning financed by the Horizon 2020 programme. His work focuses on the efficient use of heterogeneous HPC resources in a cloud setting.
Topics: Using AI in complex software stacks.
Linkedin

• Prabilistic machine learning with AMIDST code and slides zip github
• Scikit-learn tutorial with code and slides zip github

• A. Lundervold et al., MR image segmentation using deep convolutional neural networks. 

• A. Raffo, A machine learning approach to reverse engineering based on clustering and approximate implicitization 

• Vaneeda Allken, Tiffanie Schreyeck, Thomas Mahiout, Shale Rosen, Nils-Olav Handegard, Ketil Malde, Fish species identification using a convolutional neural network and simulation-based learning 

• Ø. S. Klemetsdal, O. Møyner, K.- A. Lie, Non-linear Newton Solver for a Polymer Two-phase System Using Interface-localized Trust Regions 

• Giorgia Carra, Could a Recurrent Neural Network (RNN) predict elevated intracranial pressure? 

• Alexander S. Lundervold, Jarle Rørvik, Arvid Lundervold, Fast semi-supervised segmentation of the kidneys in DCE-MRI using convolutional neural networks and transfer learning 

• Diana Karoseviciute, Evaldas Vaiciukynas, Sentiment analysis in customer reviews 

• Badreddine Benyacoub and Abdelhadi Sabrya, Comparative study of descritization methods for HMM classifiers 

• Runar Berge, Modeling fracture reactivation in a mixed dimensional setting: Friction models and numerical challenges