This is first of a series of seminars on digital twins organized by the SIRIUS Centre for Research-Driven Innovation, the PeTWIN NFR research project and the dScience centre of the University of Oslo. The first of these seminars will be given by Janne Aas-Jakobsen, CEO of Consigli AS.

The seminar will be held virtually. Please register here to be sent a link for joining the seminar. https://nettskjema.no/a/234184

The digital twin for the building and construction industry has a very strong 3D-flavour and has been driven towards the ultimate visualization rather than a rich information model to support decision making. Consigli is developing a data-driven platform, aiming to design buildings by ML, Mathematics and coded domain knowledge – a self-designing engineer as a service. With hands on experience of the gap between the digital twin (BIM) and AI in the building and construction sector, Janne, the founder of Consigli, will present the ongoing research and development, challenges and opportunities related to their work.

The post SIRIUS / PeTWIN / dScience Seminar, 1st December 2021, Digital Twins in Construction, Janne Aas-Jakobsen appeared first on Sirius.

https://ottr.xyz/event/2021-01-28-user-forum/

This event will take place virtually on Thursday 28th January 2021 at 12:00–14:00 CET. The purpose of the event is to let users of the OTTR framework share experiences and to meet the developers behind OTTR to discuss future directions. The event should also be of interest to those that are curious to see practical uses of the OTTR framework. We also welcome input and presentations of tools and technologies that are related to OTTR.

Ontology Engineering

The post 1st OTTR User Forum – 28th January 2021 appeared first on Sirius.

SIRIUS is once again heavily involved in the November Conference in Rio de Janeiro. This year the event is virtual, with a plenary on 9th November 2020 and parallel sessions on various days in October, November and December 2020. David Cameron is chairman of the program committee for the conference.

SIRIUS is also co-organizer of the session on Digitalization and Autonomy on 10th November 2020. Geir Horn and Marta Rozanska will be presenting their work in this session.

For more information, see the Innovation Norway website:

https://www.innovasjonnorge.no/en/start-page/norway-brazil-weeks/program/

The post Eighth November Conference on Norwegian-Brazilian Energy Research appeared first on Sirius.

He is s defending the thesis Low-Resource Adaptation of Neural NLP Models.

Real-world applications of natural language processing (NLP) are challenging. NLP models rely heavily on supervised machine learning and require copious amounts of annotated data. These resources are often based on language data available in massive quantities, such as English newswires. However, in real-world applications of NLP, the textual resources vary across several dimensions, such as language, dialect, topic, and genre. It is challenging to find annotated data of sufficient amount and quality. The objective of this thesis is to investigate methods for dealing with such low-resource scenarios in information extraction and natural language understanding. To this end, we study distant supervision and sequential transfer learning in various low-resource settings. We develop and adapt neural NLP models to explore several research questions concerning NLP tasks with minimal or no training data.

During his time at SIRIUS, Farhad has collaborated with Schlumberger and IBM. He was also an UTFORSK exchange fellow at the Federal University of Rio Grande do Sul.

Trial Lecture

His trial lecture will be on “Natural Language Inference: Datasets, Methods, Current Challenges and What’s Next”

The post PhD Defence for Farhad Nooralahzadeh 30th October 2020 appeared first on Sirius.

He is s defending the thesis Adaptive Query Extension Suggestions for Ontology-Based Visual Query Systems.

Many modern search systems allow users to narrow down their search by applying one or more search filters to the available data. This works well until the combination of filters becomes too restrictive, and no results remain. When this happens, the user needs to backtrack and remove the filter they just added, which is very counterproductive. In order to prevent this from happening, the search system should detect and disable too restrictive filters before the user activates any of them.

Current solutions are only able to do this in some special situations, but the solution presented in this thesis is more flexible and works in any situation.

Trial Lecture

His trial lecture will be on “Combining symbolic and non-symbolic knowledge representation for explainable AI solutions”.

A video of the trial lecture is available here:

https://www.mn.uio.no/ifi/forskning/aktuelt/arrangementer/disputaser/2020/Vidar.triallecture.mp4

The post PhD Defence for Vidar Klungre 14th October 2020 appeared first on Sirius.

Rustam Mehmandarov moderated the questions at the seminar.

Basil’s talk is in English, while the rest of the seminar is in Norwegian.

The post Public Lecture on Language Processing appeared first on Sirius.

https://2020.declarativeai.net

24 June – 1 July 2020
Oslo, Norway

Welcome to Declarative AI 2020, an event co-organised by SINTEF AS, University of Oslo, and Norwegian University of Science and Technology, under the umbrella of the SIRIUS Centre for Scalable Data Access. The event aims at presenting the latest advancements in AI and rules, reasoning, decisions, and explanations and their adoption in IT systems.

Keynote speakers:

• Derek Miers (Gartner, United Kingdom): “What The Real World Needs From Decision Management, Reasoning and AI”
• Dieter Fensel (University of Innsbruck, Austria) “Knowledge Graphs: Methodologies, Tools, and Selected Use Cases”
• Eyke Hüllermeier (Paderborn University, Germany) “Multilabel rule learning”
• Arild Waaler (University of Oslo, Norway)

Declarative AI 2020 brings together three co-located events:

1. The 4th International Joint Conference on Rules and Reasoning
   (RuleML+RR 2020) http://2020.ruleml-rr.org Target audience: Academia and industry working in the area of AI and rules
2. DecisionCAMP 2020 https://decisioncamp2020.home.blog Target audience: Digital decisioning practitioners (Business Analysts, Business Experts, Developers or Architects)
3. The 16th Reasoning Web Summer School https://2020.declarativeai.net/events/rw-summer-school Target audience: Postgraduate (PhD or MSc) students, postdocs,
   young researchers, and senior researchers

Call for contributions:

• RuleML+RR Call for Papers: http://2020.ruleml-rr.org/pages/ruleml-rr-cfp
• DecisionCAMP Call for Presentations: https://decisioncamp2020.home.blog/call-for-presentations
• RW Summer School Call for Applications https://2020.declarativeai.net/events/rw-summer-school

Core organization team

Declarative AI 2020:

Chair – Till C. Lech (SINTEF AS, Norway);

Logistics Chair – Inger-Lise Reang (University of Oslo, Norway);

Sponsorship Chair – Anders Bryhni (SINTEF AS, Norway),

Publicity Chair – Hilde Marie Fjære (SINTEF AS, Norway);

Financial Chair and Webmaster – Ahmet Soylu (NTNU / SINTEF AS, Norway)

RuleML+RR 2020:

General Chairs – Dumitru Roman (SINTEF AS / University of
Oslo, Norway), Martin Giese (University of Oslo, Norway),
Ahmet Soylu (NTNU / SINTEF AS, Norway);

Program Chairs – Víctor Gutiérrez Basulto (Cardiff University, UK), Tomas
Kliegr (University of Economics, Prague, Czech Republic)

DecisionCAMP 2020:

General Chair – Jacob Feldman (OpenRules, USA)

Reasoning Web 2020:

General Chairs – Andreas Pieris (University
of Edinburgh, UK), Marco Manna (University of Calabria, Italy)

Interested to become a sponsor for the event? Check out available sponsorship packages at https://2020.declarativeai.net/sponsors.

Check out further details at https://2020.declarativeai.net, and see you in Oslo!

The post Declarative AI 2020 appeared first on Sirius.

Time: 14:15-15.00 NB New Time!

Place: SIRIUS meeting room (8459). 8th Floor, Ole-Johan Dahls hus.

Chi Mai Nguyen, our new postdoctoral researcher at SIRIUS, will present a short introduction about SMT (a technique for deciding the satisfiability of properties expressed as of qualifier-free first order formula) and a brief explanation how to use SMT in problem solving.

Satisfiable Modulo Theories is the problem of deciding the satisfiability of qualifier-free first order formula with respect to some decidable theories. Many efficient SMT solvers were able to handle optimisation problems with up to thousands Boolean/rational variables. It would be a great benefit to exploit the advantage of SMT solvers in problem solving and optimising. This talk gives a short introduction about SMT and a brief explanation how to use SMT in problem solving.

Chi Mai Nguyen is a postdoctoral researcher at the SIRUS centre, Department of Informatics, University of Oslo. She obtained her Master  degree in Theoretical Computer Science at Aalto University, in 2012. In April 2017, she received her PhD degree at University of Trento with the thesis entitled “Efficient Modelling and Reasoning with Constrained Goal Models”. Her work mainly focuses on formal verification, model checking, and applying automated reasoning techniques (mostly SAT and SMT) to goal models. She is a member of the Analysis of Complex Systems research program and will be working in the Integrated Digital Planning beacon.

The post Seminar August 23 2019: SAT- and SMT-based automated reasoning appeared first on Sirius.