There are individuals who are immensely knowledgeable. And yet, as Maria von Ebner-Eschenbach tells us, “knowledge expands when it is shared.” But does knowledge that has been gathered in vast knowledge bases always remain free of errors? And how does one go about drawing accurate conclusions from collected knowledge? Patrick Rodler, Post Doc at the Department of Applied Informatics, is working on artificially intelligent error detection and error correction in knowledge bases.

One of his current projects is a collaboration with Stanford University, which revolves around keeping the knowledge bases of the National Cancer Institute in New York as free of errors as possible. These medical data bases contain hundreds of thousands of logical sentences referring to various forms of cancer, recorded by medical professionals, from which researchers aim to deduce correlations between symptoms, genes, causes and treatment options.

It stands to reason, Patrick Rodler observes, that such a vast amount of data, entered in the form of logical sentences, will inevitably produce discrepancies. “In fact, there are even instances of tiny knowledge bases, containing as little as three sentences, which are contradictory in themselves, where yet experienced knowledge engineers or experts are unable to identify the error, still less to remedy it. This is the point where our methods provide assistance.” Following an automated process, these methods reduce the complicated problem of error detection to a sequence of true-false questions, such as “Does every tumour cause pain?” These questions are submitted to a qualified expert for evaluation; in this case it would be a doctor who interacts with the system. The expert’s responses subsequently prompt a gradual limitation of possible errors. For this process to work as intended, it is essential to provide the user with an optimal level of support accompanying the interaction with the diagnosis tool. “Our newest procedures permit the highly efficient generation of easily comprehensible expert questions, and automatically adapt the content of these questions to the available expert knowledge. What conventional methods do in hours, our system can achieve in a fraction of a second”, Rodler elaborates. This saves valuable time for the experts, and reduces the amount of effort required on their part. “One way of picturing our systems is to imagine a metal detector that is searching for the famous needle in a haystack.”

Knowledge bases of this type are formulated with the help of logical languages. Although these cannot be used to express quite as much as in a natural language, their formal character nonetheless allows systems to automatically draw conclusions, establish correlations, extract relevant information, or answer complex questions. “They offer a way to realise artificially intelligent medical systems.” To give an example: If the availability of data about the symptoms, genetic dispositions and treatment methods for a particular type of cancer is good, it is possible to calculate what the best recommendation for a new patient might be. “The sum of knowledge thus creates enormous added value – provided that the underlying knowledge base is flawless.”

Knowledge generated at the Department of Applied Informatics is gaining currency across the globe: Working in collaboration with his colleagues, Patrick Rodler has developed a plug-in for the “Protégé” programme, the most widely used Open Source tool for knowledge base engineering worldwide, which boasts around 330,000 users. The plug-in has already reached a download tally of roughly 37,000.

Error detection in knowledge bases is only one of several practical applications, which Patrick Rodler is working on. He is generally interested in “artificially intelligent error detection in the broader sense”. This means that the technologies developed are endowed with broad applicability – be this in hardware systems (i.e. computer chips or cars), in software programmes or in planning systems (for transport logistics, for instance). The methods can be applied to any system that can be appropriately modelled, where errors need to be detected and remedied.

The notion that knowledge as a commodity expands when it is shared is a belief that Patrick Rodler also holds as a teacher: “I love teaching. In my courses, I endeavour to treat complex content in such a way that everyone can understand it. Because I also had to learn these things in the past, I pay particular attention to providing good explanations for aspects I once struggled with myself. I consider the objective achieved, when my students are quicker to grasp things than I once was.” Originally, Patrick Rodler wanted to study languages, but decided to tackle Technical Mathematics first, and later added Informatics. He currently holds Master’s degrees in both Mathematics and Informatics, as well as a doctorate in Informatics – having achieved top grades in all subjects in all these studies. In January he received a “Recognition Award 2013-2016 of the Austrian Society for Artificial Intelligence” for his Master thesis “A Theory of Interactive Debugging of Knowledge Bases in Monotonic Logics”. Any person treading a path of this level of intensity also needs to find the right kind of balance. “My family provides the best environment that I can possibly imagine. I’m also a regular and keen sportsman.” As such, Patrick Rodler has two Carinthian Academic Football Championship titles to his name. To him, his work in teaching and research “feels a lot like a hobby. I hardly ever mind getting stuck in, even if it’s the weekend.” Quite often, he finds himself reading specialist literature in his leisure time. “There are simply so many interesting things to discover and to know”, Rodler explains.

When asked about the many bleak future scenarios involving artificial intelligence as depicted on TV, he responds as follows: “I firmly believe that the number of scientists who strive to advance artificial intelligence for the benefit of mankind will always be greater than the number aiming to exploit it for criminal purposes. Thus, ‘good AI’ should hopefully always manage to keep a step ahead of ‘bad AI’. That is why I am pretty optimistic about the future developments in this field.”

Der Beitrag Artificially intelligent metal detector for the needle in the haystack of knowledge erschien zuerst auf Alpen-Adria-Universität Klagenfurt.

Source: AAU TEWI

The EU H2020 project TRACES combines the spheres of the arts and science to encourage the joint development of new discussion spaces dedicated to contentious and painful historical events, the effects of which continue to unfold, even today. The project, which has now entered the second of three stages, has been awarded the “European Year of Cultural Heritage 2018 (EYCH) label”. In this interview, project co-ordinator Klaus Schönberger, professor at the Department of Cultural Analysis, talks about the insights that have been gained so far.

What are you hoping to know by the time you reach the end of the project?

We are dealing with aspects of our cultural heritage that are contentious, painful, problematic, and that continue to affect our co-existence to this very day. The term for this is “contentious heritage”. This label describes events that aren’t necessarily proudly displayed as badges of achievement on the basis of which one might confidently state: ‘This is who I am. Or: This is who we are.’ Very often, artists and performers are invited to create interventions addressing such events. In our view, this is an unsatisfactory approach as, in many cases, it has no lasting effects. However, we are convinced that it is possible, using art, to create a space for hostile parties or opposing sides, with a language that permits communication about the event, without everyone immediately taking up their position in the trenches. That, at least, is our noble aim.

Can you provide an example?

One of our sub-projects takes place in Northern Ireland. The point of origin for this sub-project is Maze Prison, also known as Long Kesh. Between 1971 and 2000 this was a maximum security prison, and during the civil war its prisoners included both Republican and Protestant activists, who had been accused of acts of terrorism. The now vacant prison complex, with all the conflicts that were carried out in that location, represents what we refer to as a site of “contentious heritage”. Each side projects its own experiences and recollections onto this site. Today, two artists (Martin Krenn and Aisling O’Beirn) are working there to establish communications between parties involved on either side of the conflict. When Marion Hamm and I held a lecture there, a certain reservation amongst the people in attendance was obvious even to us. But they were all sitting in the same room. The aim of the artistic interventions is not to resolve the conflict, but to open up a space in which the distinct positions are recognised, without going for each other’s throat. TRACES hopes to contribute to allowing conflict to be carried out as a difference of interests that avoids violent eruptions. We refer to this as the re-politicization of the conflict.

Why do you believe that the arts are better suited to this job?

At first, I was not at all convinced that this is the case. But I always asked myself: What is it that the arts know, and I don’t? For me, the difference between the arts and ethnographic research is that the former obscure, while the latter uses scientific procedures to enlighten. We perceive obscuration as an opportunity, because it generates other associative spaces. In other words, we are searching for ways in which the obscuration produced by the arts can yield valuable new insights.

You want to argue about controversial issues, but you want this to happen in a non-violent manner. Is constant argument really necessary?

Yes, that is a primary premise of our approach. We are confident that it is not possible to have democracy without conflict. Conflict itself is not the problem, neither in Northern Ireland, nor in Europe in general. It is impossible for us to imagine Europe as anything other than a conflict-laden space, in which different interests are perpetually fought out. Our aim is not to create a European identity, but to contribute to a shared European imagination. That is a more nebulous proposition, but it is also more realistic, because many can join in the imagining. The EU, in its role as contracting entity, encourages us to experiment and to be radical in our explorations. This freedom and flexibility in terms of content is sometimes at odds with the strict administration, which can be a tremendous challenge for all of us, particularly at the intersection of science and the arts.

How many of these local projects are there in total?

All in all, there are eleven partners in ten countries, though they all feature quite distinct set-ups. Five art projects operate as so-called “creative co-productions”. In addition to the prison example in Northern Ireland, an exhibition is due to open in Edinburgh in June, which takes a look at how we deal with “Human Remains” from colonial times. In Krakow, a team comprised of artists, performers, and scientists is addressing Holocaust “folk art”, Ljubljana has hosted an exhibition featuring death masks, and a project in Romania is dedicated to remembering the Jewish cultural heritage in Transylvania and the mass emigration after 1945. To mark the end of the project we aim to put together a compendium of all the experiences here in Klagenfurt – and therein lies the particular challenge for the co-ordinator of such a giant project. This will involve the reflection of the different operating logics of science and the arts, and the European local dimension. It is our hope that this will serve to safeguard insights and allow them to unfold a sustained impact.

How do you intend to proceed?

We will reflect on the results analytically and through the use of examples, and we will consolidate our experiences. One of the challenges we face is to somehow simultaneously satisfy the scientific requirements and also the specific application-oriented expectations of the EU Commission.

Der Beitrag Conflict as part of a European democracy erschien zuerst auf Alpen-Adria-Universität Klagenfurt.

Source: AAU TEWI

Peter Schartner, data protection expert at the Institute of Applied Informatics, shows how much you can find out about a person using an e-mail address.

Find out more here!

Der Beitrag How much you can find out about a person with an email address erschien zuerst auf Alpen-Adria-Universität Klagenfurt.

Source: AAU TEWI

Benjamin Hackl begann mit 15 Jahren zu studieren, mit 20 Jahren hat er sein Masterstudium der Mathematik abgeschlossen. Er ist damit der jüngste Absolvent eines Masterstudiums an der Alpen-Adria-Universität. Heute arbeitet er als Doktorand am Institut für Mathematik.

 

Können Sie sich noch an Ihre ersten Studientage erinnern? Was war besonders, neu, auffällig, amüsant etc.

Mein Studienbeginn war besonders, weil ich mein Studium im Frühjahr 2010 parallel zur Schule als außerordentlicher Student begonnen habe – was ich aber auch rückblickend sofort wieder tun würde. In meinen ersten Kursen habe ich noch versucht, so unauffällig wie möglich zu bleiben – mit sehr eingeschränktem Erfolg…

 

Was sind Ihre Arbeitsaufgaben? Wie sieht Ihr beruflicher Alltag aus und was ist es, das Ihnen in Ihrem Job besonders gefällt?

Meine Arbeitsaufgaben sind das Verfassen meiner Dissertation, Mithilfe bei der Gestaltung der Lehre, und diverse administrative Tätigkeiten. Das macht meinen Arbeitsalltag auch sehr divers (Forschung mit Stift, Papier und Computeralgebra, Vorbereiten von Übungen und Vorlesungen, E-Mails, …), was ich sehr schätze. Insbesondere gefallen mir die beruflichen Reisen (Konferenzen, Besuch von KollegInnen) sowie die weitgehend freie Zeiteinteilung.

 

War Ihr Studium für Ihre heutige Tätigkeit hilfreich und welchen Einfluss hatte Ihr Studium auf Ihre berufliche Tätigkeit(en)?

Mein Studium war notwendig für meine jetzige Beschäftigung: ohne Master auch kein Doktorat.

 

Fällt Ihnen eine nette Anekdote aus Ihrer Studienzeit ein? Gibt es eine Situation in der Sie ans Studium/ eine bestimmte LV/ einen Prof zurückgedacht haben?

Ein überwiegender Anteil der vielen erlebten Geschichten ist wohl nur lustig, wenn man selbst dabei war – ich erinnere mich aber immer wieder gerne an die vielen Stunden, die ich mit meinen Studienkolleginnen gemeinsam in einem der ehemaligen Informatik-Labore verbracht habe.

 

Würden Sie heute nochmal dasselbe studieren?

Ja, ohne zu zögern.

 

Was würden Sie heutigen Studierenden mit auf den Weg geben?

Für ein technisches Studium benötigt man (nicht nur, aber) gerade am Anfang eine ordentliche Portion Durchhaltevermögen – Durchbeißen zahlt sich aber auf verschiedenen Ebenen aus!

 

Was vermissen Sie aus Ihrer Studienzeit (an der AAU)?

Viele meiner StudienkollegInnen sind mittlerweile mit ihrem Studium fertig und nicht mehr so leicht auf einen Kaffee in der Aula zu treffen. Ansonsten: Nichts, da ich meine Zeit immer noch an der AAU verbringen darf.

 

Der Beitrag Mathematiker Benjamin Hackl im Gespräch über seine Studienzeit erschien zuerst auf Alpen-Adria-Universität Klagenfurt.

Source: AAU TEWI