What’s the size of a concept?

A few weeks ago, I got the notification that my paper “Measuring Relations between Concepts in Conceptual Spaces” [1] (preprint available here) was accepted at the British SGAI Conference on Artificial Intelligence.

One of the question that I discuss there is posed in the title of this blog post: What’s the size of a concept?

In general, one can say that the size of a concept in a conceptual space tells you something about its specificity: Small concepts (like Granny Smith) are more specific, whereas large concepts (like fruit) are more general.

But how exactly can we measure the size of such a concept within my proposed formalization? My paper [1] gives a mathematical response to that, and today I would like to sketch the basic idea behind it.

Continue reading “What’s the size of a concept?”

Convex regions in a conceptual space are problematic

Recently, another one of my papers [1] (look at the preprint here) has been accepted at the German Conference on Artificial Intelligence. It is a quite technical paper with a lot of formulas, but I’ll try to illustrate the overall high-level idea in this and one or two future blog posts.

Today I would like to talk about the starting point of the research presented in this paper: The observation that convex regions in a conceptual space are highly problematic if we want to represent correlations between domains.

Continue reading “Convex regions in a conceptual space are problematic”

Dagstuhl Seminar “Human-Like Neural-Symbolic Computation”

Last week, I had the chance to spend five days at Schloss Dagstuhl learning, talking, and thinking about “Human-Like Neural-Symbolic Computation”.

Usually, one can distinguish two kinds of approaches in artificial intelligence: Symbolic approaches are based on symbols and rules, mostly in the form of logic. They are good for encoding explicit knowledge as for example “all cats have tails”. Neural approaches on the other hand typically work on raw numbers and use networks of artificial neurons. They are good for learning implicit knowledge, e.g., how to recognize cats in an image. All participants of this invitation-only seminar are actively working on combining these two strands of research.

Continue reading “Dagstuhl Seminar “Human-Like Neural-Symbolic Computation””

Interdisciplinary College 2017

Last week, I participated in this year’s interdisciplinary college (https://www.interdisciplinary-college.de). In the course of this spring school, I was able to meet many other students working on exciting research projects. By taking lectures, I acquired basic knowledge of neuroscience, some ideas about creativity (both from the behavioral/neural viewpoint as from the AI perspective) and many impulses on language grounding in robotics.

I was also able to present my overall PhD research project (“Concept Formation in Conceptual Spaces”) both during the poster session and as a “rainbow course” lecture. On both occasions I got very valuable feedback and stimulating impulses for my further research. I’ve uploaded the respective resources in case you are interested: the pdf file of my poster and the slides of my presentation.

Long story short: it was a great week with a lot of input and impulses. 🙂