by Sander Bohte (CWI)  and Hung Son Nguyen (University of Warsaw)

While the discipline of machine learning is often conflated with the general field of AI, machine learning specifically is concerned with the question of how to program computers to automatically recognise complex patterns and make intelligent decisions based on data. This includes such diverse approaches as probability theory, logic, combinatorial optimisation, search, statistics, reinforcement learning and control theory. In this day and age with an abundance of sensors and computers, applications are ubiquitous, ranging from vision to language processing, forecasting, pattern recognition, games, data mining, expert systems and robotics.

by Jean-Baptiste Mouret (Inria)

Many fields are now snowed under with an avalanche of data, which raises considerable challenges for computer scientists. Meanwhile, robotics (among other fields) can often only use a few dozen data points because acquiring them involves a process that is expensive or time-consuming. How can an algorithm learn with only a few data points?

by Peter Wittek (ICFO-The Institute of Photonic Sciences and University of Borås)

It is not only machine learning that is advancing rapidly: quantum information processing has witnessed several breakthroughs in recent years. In theory, quantum protocols can offer an exponential speedup for certain learning algorithms, but even contemporary implementations show remarkable results – this new field is called quantum machine learning. The benefits work both ways: classical machine learning finds more and more applicability in problems in quantum computing.

by Max Welling (University of Amsterdam)

In our research at the University of Amsterdam we have married two types of models into a single comprehensive framework which we have called “Variational Auto Encoders”. The two types of models are: 1) generative models where the data generation process is modelled, and 2) discriminative models, such as deep learning, where measurements are directly mapped to class labels.

by Bernd Malle, Peter Kieseberg (SBA Research), Sebastian Schrittwieser (JRC TARGET, St. Poelten University of Applied Sciences), and Andreas Holzinger (Graz University of Technology)

While machine learning is one of the fastest growing technologies in the area of computer science, the goal of analysing large amounts of data for information extraction collides with the privacy of individuals. Hence, in order to protect sensitive information, the effects of the right to be forgotten on machine learning algorithms need to be studied more extensively.

by Wouter M. Koolen (CWI)

Machine learning systems for sequential decision making continuously improve the quality of their actions. Our new adaptive methods learn to improve as fast as possible in a wide range of applications.

by Karol Kurach (University of Warsaw and Google), Marcin Andrychowicz and Ilya Sutskever (OpenAI (work done while at Google))

We propose “Neural Random Access Machine”, a new neural network architecture inspired by Neural Turing Machines. Our architecture can manipulate and dereference pointers to an external variable-size random-access memory. Our results show that the proposed model can learn to solve algorithmic tasks and is capable of discovering simple data structures like linked-lists and binary trees. For a subset of tasks, the learned solutions generalise to sequences of arbitrary length.

by Olof Görnerup and Theodore Vasiloudis (SICS)

In machine learning, similarities and abstractions are fundamental for understanding and efficiently representing data. At SICS Swedish ICT, we have developed a domain-agnostic, data-driven and scalable approach for finding intrinsic similarities and concepts in large datasets. This approach enables us to discover semantic classes in text, musical genres in playlists, the genetic code from biomolecular processes and much more.

by Claudio Lucchese, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto  (ISTI-CNR), Salvatore Orlando (Ca’ Foscari University of Venice) and Rossano Venturini (University of Pisa)

The complexity of tree-based, machine-learnt models and their widespread use in web-scale systems requires novel algorithmic solutions to make the models fast and scalable, both in the learning phase and in the real-world.

by Mark Cieliebak (Zurich University of Applied Sciences)

Deep Neural Networks (DNN) can achieve excellent results in text analytics tasks such as sentiment analysis, topic detection and entity extraction. In many cases they even come close to human performance. To achieve this, however, they are highly-optimised for one specific task, and a huge amount of human effort is usually needed to design a DNN for a new task. With DeepText, we will develop a software pipeline that can solve arbitrary text analytics tasks with DNNs with minimal human input.

by András A. Benczúr, Róbert Pálovics (MTA SZTAKI) , Márton Balassi (Cloudera), Volker Markl, Tilmann Rabl, Juan Soto (DFKI), Björn Hovstadius, Jim Dowling and Seif Haridi (SICS)

Big data analytics promise to deliver valuable business insights. However, this will be difficult to realise using today’s state-of-the-art technologies, given the flood of data generated from various sources. The European STREAMLINE project develops scalable, fast reacting, and high accuracy machine learning techniques for the needs of European online media companies.
Big data analytics promise to deliver valuable business insights. However, this will be difficult to realise using today’s state-of-the-art technologies, given the flood of data generated from various sources. The European STREAMLINE project [L1] develops scalable, fast reacting, and high accuracy machine learning techniques for the needs of European online media companies.

by Frederic Alexandre (Inria)

Inspiration from human learning sets the focus on one essential but poorly studied characteristic of learning: Autonomy.

by Pierre-Yves Oudeyer, Manuel Lopes (Inria), Celeste Kidd (Univ. of Rochester) and Jacqueline Gottlieb (Univ. of Columbia)

Autonomous lifelong multitask learning is a grand challenge of artificial intelligence and robotics. Recent interdisciplinary research has been investigating a key ingredient to reach this goal: curiosity-driven exploration and intrinsic motivation.

by Jan Stampfli and Kurt Stockinger (Zurich University of Applied Sciences)

A novel alarm verification service applying various machine learning algorithms can identify false alarms.

by George Potamias (FORTH)

Within the framework of the Greek eMoDiA (electronic PharmacoGenomics Assistant) project, we developed an electronic pharmacogenomics assistance platform using machine learning techniques.

by José Francisco García Cantos, Manuel Peinado, Miguel A. Salido and Federico Barber (AI2-UPV)

Metaheuristic techniques can help to optimise various industrial processes. These techniques can be used, for example, to help plan cutting processes in continuous float glass manufacturing, resulting in reduced losses due to material defects.

by Balázs Csanád Csáji, András Kovács and József Váncza (MTA SZTAKI)

One of the key problems in renewable energy systems is how to model and forecast the energy flow. At MTA SZTAKI we investigated various stochastic times-series models to predict energy production and consumption, and suggested an online learning method which can adaptively aggregate different forecasts while also taking side information into account. The approach was demonstrated on data coming from a prototype public lighting microgrid containing photovoltaic panels and LED luminaries.

by Bert Kappen and Wim Wiegerinck (University Nijmegen)

Bonaparte is a software application developed by Smart Research, a subsidiary of SNN at Radboud University Nijmegen, which uses Bayesian Networks to quickly identify a large number of disaster victims.