The year is coming to an end, Christmas is around the corner, and reviews of 2017’s events are popping up everywhere. I think this is a nice opportunity to also look back at the year 2017, to summarize what has happened in my academic life, and to speculate a bit about 2018.
In my last blog post, I have introduced the general idea of Logic Tensor Networks (or LTNs, for short). Today I would like to talk about how LTNs and conceptual spaces can potentially fit together and about the concrete strands of research I plan to pursue.
It’s nice to have a mathematical definition of concepts in a conceptual space. It’s also nice that we can create new concepts based on old ones, for instance by intersecting them. But being able to talk about the relation of two concepts is certainly also useful. Last time, we talked about the size of a concept. We can use the size of concept to figure out that the concept of “animal” is more general than the concept of “Granny Smith” – simply because it is larger.
But there are also other ways of describing the relation of two concepts. Two of them, namely subsethood and implication, will be presented in today’s blog post.
A few weeks ago, I got the notification that my paper “Measuring Relations between Concepts in Conceptual Spaces”  (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  gives a mathematical response to that, and today I would like to sketch the basic idea behind it.
As stated earlier, the goal of my PhD research is to develop a system that can autonomously learn useful concepts purely from perceptual input. For instance, the system should be able to learn the concepts of apple, banana, and pear, just by observing images of fruits and by noting commonalities and differences among these images.
So far, I have mainly been talking about the conceptual spaces framework and how we can mathematically formalize it. However, as I want to actually end up with a running system, I need to implement my formalization in a computer program. So in today’s blog post, I’d like to introduce my implementation, which is publicly available: https://github.com/lbechberger/ConceptualSpaces