Explainable AI

With ever more powerful and ubiquitous artificial intelligence (AI) questions arise about how these inscrutable black-box systems arrive at their decisions, which can have serious legal or health-related consequences, such as in autonomous cars or tumor recognition.

In 2016 the US Department of Defense (DARPA) started an initiative on explainable AI (XAI) to investigate how to answer these questions. In May 2018 the EU’s General Data Protection Regulation (GDPR) will come into effect, with especially article 21 “Right to object” and article 22 “Automated individual decision-making, including profiling” giving subjects the right to object against ‘any decision based solely on automated processing[, meaning AI], […] which produces legal effects concerning [the subject] or similarly significantly affects him or her.’ (cited from article 22)

In the light of these initiatives to investigate and to regulate the usage and misuse of AI, we will have a look at and discuss both the technical concepts and solutions at play, and the regulatory law and how to devise it such that it works to the greatest benefit of all.

Therefore, please read at least the material of level 1 to prepare for our next meeting on Wednesday 31st January 7:30pm 2018 in Tunnel Vienna, Florianigasse 39, 1080 Vienna.


Level 1

Read this very accessible article on the topic by the the New York Times.

Level 2

Also read these articles critical towards the GDPR and the DARPA viewpoint, and have a look at the Wikipedia articles on XAI and the Right to Explanation as attempted to be installed in the GDPR.

Level 3

Dig deep into the legal framework of the EU’s GDPR (especially Recital 71) and see for yourself how this affects future AI development.


Picture credit: https://tctechcrunch2011.files.wordpress.com/2015/11/humanrobotoverlap.jpg?w=738

First meeting of season three

We will start off the new season of the Naturwissenschaftscafé with a meeting in the Tunnel Vienna (Florianigasse 39, 1080 Vienna) on Monday 2nd October.

We will be discussing on which day and time the NWC should be held and what is up for new topics. This is also a great opportunity to get to know the regular attendees and get introduced to our group.


The Vienna Circle and its Philosophy

The next Naturwissenschaftscafé will take place on Friday 21st April at 6pm at Strudlhofgasse 4. The topic will be the Vienna Circle and its philosophy.

Please read into to material provided below to prepare for the meeting.

Level 1
To get an overview of the Vienna Circle just have a look at the Wikipedia article:

Level 2
For a bit more background there are some sources I can suggest you to look into:

Interview of A.J. Ayer on Logical Positivism and its Legacy : https://www.youtube.com/watch?v=nG0EWNezFl4

Prof. Christian Damböck, who also held a talk on the Symposium, wrote a book about the Vienna Circle (Ausgewählte Texte des wiener Kreis). He published a postface which I strongly suggest you to read (unfortunately in German): Nachwort zu Ausgewählte texte des wiener Kreis:

Level 3
For those of you, that really want to spend more time learning about the Vienna Circle, read the following:

Book (which I will bring with me to the NWC): Sie nannten sich der Wiener Kreis, exaktes denken am rande des Untergangs by Karl Sigmund

and the article of Stanford Encyclopedia of Philosophy:

How to choose the right Quantum Interpretation: Macrorealism, Contextuality and Decoherence

The next NWC will be held upcoming Friday 7th April at 6pm at the faculty of physics in Strudlhofgasse 4.

First, I would like you to revisit the materials from last time about Bells Inequality and local realism. Also Flavio already included nice material about Leggett-Garg Inequalities and macrorealism.

Second, here are my resources:

Level 1: I will cover basically the Legget-Garg and Kochen-Specker Theorems and how they could be experimentally tested to rule out certain QM Interpretations similar to Bell’s Inequality and local realism. A good starting point:

Level 2: Kofler and Bruckner have written a nice comparison between Bell and L-G, also thinking about experiments that violate macrorealism:
And (my all-time favorite) Stanford Encyclopedia of Philosophy has a review over Kochen-Specker and it’s implications:

Level Experimental Metaphysics:
Well, in one meeting we probably won’t have time to cover more, but for the sake of completeness on experimental tests of quantum foundations, one has to add the current notion of decoherence as most promising solution to the measurement problem. Also this gives an idea why the many-worlds interpretation gains momentum right now.

Here is a recent overview of how decoherence relates to different interpretations:

And the legendary lecture of Harvard Professor Sidney Coleman “Quantum Mechanics in your Face”:

Non-Locality and Macroscopic Realism

At our next meeting on 23rd March at 8pm we will discuss the topic of non-locality and macroscopic realism in quantum mechanics and its philosophical implications. For this please have a look into the material provided below. There are different levels you can choose from.

Level 1
Read the Presentation on non-locality and macrosopic realism and have a look at the basis of Bell’s theorem as a background.

Level 2
Read the more in in-depth paper on Condition for macroscopic realism beyond the Leggett-Garg inequalities.

Level 3
Read the full contemplation on Bell’s Inequalities: Foundations and Quantum Communication.

The Theory of Memes

Our next meeting will be held on 9. January 2017 at 8pm in the Café der Provinz.
There Annie will present the theory of memes.

Please prepare and read and go through the provided information below.

Level 1
Read https://en.wikipedia.org/wiki/Meme
or watch this video https://www.youtube.com/watch?v=6iHZi-z7H4o

Level 2
Watch https://www.youtube.com/watch?v=HV9WEqLeBuo
or with this video with some additional theory https://www.youtube.com/watch?v=fQ_9-Qx5Hz4

Level 3
Read the book Dawkins – The Selfish Gene for more detaild information