CITIUS once again brings together science and business to ‘teach’ AI how to explain itself.

CITIUS, a member of the CIGUS Network, which comprises those centres whose research quality and impact has been accredited by the Galician Autonomous Government (Xunta de Galicia), is promoting a new international event that will be held on 15th and 16th December in Utrecht (The Netherlands). It will once again bring together professionals from academia and industry to discuss how the quality of algorithms in a cutting-edge emerging research area known as Explainable Artificial Intelligence (XAI), a field of study which faces the challenge of making AI systems self-explanatory, should be assessed.

Scientists from a number of European universities in the United Kingdom (Aberdeen), Ireland (Dublin) and The Netherlands (Tilburg, Utrecht), together with representatives from industry (such as Philips or Trivago), will share their experiences with PhD students within the framework of the European Training Network NL4XAI (Interactive Natural Language Technologies for Explainable Artificial Intelligence). This is a research project funded under the European Union’s Horizon 2020 programme, geared towards training the first generation of European experts in the field of Explainable Artificial Intelligence.

A training event for quality assessment

Eleven PhD students (also known as Early-Stage-Researchers, ESRs) form the core of this project: they will face the challenge of enabling Artificial Intelligence systems to explain themselves in order to enhance the use of these emerging techniques.

Essentially, next month’s event will provide these students with hands-on experience in designing assessment experiences. A key issue will be the widely reported experience in experimental sciences that experiments can be extremely difficult to replicate. One of the possible reasons for this is that crucial details may be missing from the research articles in which the experiments are reported, or because of statistical issues.

Students will obtain experience in identifying these problems in existing studies, whilst learning to work in a way that will ensure the replicability of the assessment studies they will conduct in the remainder of their PhD projects. Registration and further information about the event are available at the NL4XAI Training Days’ Official Website.

H2020 Training Network

NL4XAI is funded by the Horizon 2020 research and innovation programme, through a Marie Skłodowska-Curie grant, within the framework of the European Union’s commitment to Explainable Artificial Intelligence. The network is coordinated by the research team at the Centre for Research into Intelligent Technologies at the University of Santiago de Compostela (CiTIUS-USC), led by Senén Barro. NL4XAI is a joint academic-industry research network that brings together 19 beneficiaries and partners from six different European countries (France, Malta, Poland, Spain, The Netherlands, and the UK). The partners include two national research institutions (IIIA-CSIC, CNRS), ten universities (University of Aberdeen, University of Dundee, L-Universitá ta’ Malta, Delft University of Technology, Utrecht University, University of Twente, Warsaw University of Technology, Université de Lorraine, Universidade de Santiago de Compostela, Universitat Autonòma de Barcelona, Maastricht University) and six private companies (Indra, Accenture, Orange, Wizenoze, Arria and InfoSupport).