Tutorials

The rampant outbreak of the novel coronavirus (COVID-19, SARS-Cov-2), during early December 2019 in Wuhan, China, has created a staggering worldwide crisis along with the widespread loss of lives. The scarcity of resources and lack of experiences to endure the COVID-19 pandemic, combined with the fear of future consequences has established the need for the adoption of Artificial Intelligence (AI) techniques to address the challenges. Motivated by the need to highlight the need for employing AI in combating the COVID-19 pandemic, this tutorial aims to help the audience to gain a comprehensive understanding of the current state of AI applications in developing the computer-assisted (controlling, monitoring, discovery, diagnosing and treatment) systems to battle the COVID-19 crisis along with the AI-assisted spread containment measures.

This tutorial presents the recent advances in deep learning based data fusion techniques specifically for three main computer vision tasks: classification, detection and segmentation.

In this tutorial we will present and discuss the practical challenges of applying Explainable AI (XAI) in the financial services industry. We will cover user requirements and evaluation, concept-based explainability and learning to explain from human interaction, as well as, how to explain recurrent models.

In this tutorial, we discuss the broad spectrum of matrix factorizations where the approximation error in terms of the Frobenius norm is minimized. Our goal is to provide a rich but clear basis knowledge about the matrix factorization zoo, along with recent advances in (nonconvex) optimization theory which inspire to find novel solutions to longstanding problems.

Humans can learn very effectively from few examples, because we almost never learn new tasks from scratch, but draw on everything we have learned before. Meta-learning emulates this approach in many different ways. This tutorial covers the key methods underlying the current state of the art in this fast-paced field.

Hands-on tutorial on machine learning tools for machine learning for data streams. This tutorial is an introduction to River in Python and MOA in Java, software environments for implementing algorithms and running experiments for online learning from evolving data streams.

The goal of this tutorial is to offer a comprehensive presentation of role analytics in networks with focuses on role discovery, role-oriented network embedding, and role-based applications.

A Hands-on Tutorial showing the services provided by SoBigData Research Infrastructure or the new generation of Responsible data science.