Leonid Perlovsky

I´m now something like a platonic love with Leonid Perlovsky. It is full of news, full of surprises, disgust and also happiness from discovering new areas.

Let's introduce my story. From the beginning of my PhD.studies I have started to read a lot. After half a year I had read enough to know something but not enough to be good at something. Michal asked me to read and try to understand L.Perlovsky and his theory which he thought could be very interesting for him. He is playing with growing neural networks and some cognitive architectures. My task was to look deeper into the Neural field theory (which is the theory introduced by Leonid Perlovsky) and try to implement it.

After reading a lot of papers and also one book I started to understand at least a little what he is talking about. Or I thought I understand. That was totally new field for me, because I have never spent time with clustering, classification or other data mining methods before. So I was something like a blind man who is listening how does the world around look like. My view on his theory was a little bit strange because I didn't know relevant theories on which he is building his new approach. But let say that after few months I was able to work with it and I´ve even tried to implement the method in Matlab.

Until today I haven't been very successful, but I'm progressing. What is it all about and why I'm now a little bit sceptical?

The idea of this theory is that the bottom-up and top-down approaches are meating. Both data and model have some fuzziness and while it is approaching each other it is getting more and more crisp. Starting with some very fuzzy gaussian model it is starting to be more crisp when the fuzziness is getting smaller (he calls this dynamic fuzzy logic). The main idea is that when the error rate is starting to increase we will add new model and watch if there will be decrease in the errorness. When we find the best number of models we will try to change the parameters and approximate the data. So from the very fuzzy gaussian model with low number of parameters we are getting to the set of crisp parametrized models. With this approach Perlovsky is hoping to defeat the curse of dimensionality and the computational complexity which is so problematic in these clustering methods.

What was very strange and instructive for me was, when I read the book about feature selection computational methods and afterwards some dissertation thesis about Gaussian mixture models. What a surprise. This huge theory which was introduced for NASA is only Gaussian mixture model with fuzziness and nice biological and philosophical background. So nothing strange. But why he doesn't mention this? To confuse me as a novice in this area? It could be much easier to know all these things, because GMM are implemented and very well described. So I could only work on the improvements of the method and my task wouldn't be to start from the beginning and look for some relevant information in the big book full of philosophical and metaphysical thoughts.

So it is another advice for me before I start with some other thing.
Now I hope the work will continue much quicker having know all these things. Because I must admit that I'm quite fed up with searching and trying. Want some support in the results.

Bio-inspired cognitive modeling or cognitive modeling?

Our lab haven't started yet and there was huge discussion about the name. Surely it is very important what will your name be. But what is interesting is that the discussion wasn't about the personal preferences but it went deeper.

We have discussed whether it is even possible to talk about cognitive modeling as bio-inspired cognitive modeling. Is cognition only functionalism phenomenon independent on the substrat or is it strictly biological phenomenon?

When we see it from the functionalism view then we focus on the functional ralations and it can be realized also in the robotics environment. Bio-inspired cognitive modeling is possible.

But there is also other point of view when we consider cognition as a strictly biological phenomenon. So it is allways related to the biological reality and bio-inspired cognitive modeling is nonsense (or at least repeated information). Because bio-inspiration could mean that we only construct some artificial system which isn't model in the real meaning - there is nothing to validate. From the model which isn't real system I can't also get inspiration how does the real biological system work.
Or does bioinspiration mean that we are constructing models which are trying to be nearly as complex and universal as the brain functioning is?

Does exist cognitive modeling which isn't bio-inspired? Something like we try to model cognition in the robot without any knowledge of the human brain? Is it still cognitive modeling?

So what will we be focused on?
What is bio-inspiration, cognition, intelligence? Too many words which have nearly lost their specific meaning and are nowdays used as something very fuzzy.
(this was mainly discussed by Matěj Hoffman and Michal Vavrečka)

We have searched the google and I have found also conference which name was "Bio-inspired modeling of cognitive tasks". So there are at least different interpretations. Or is it misused in this case?

Further Matěj mentioned the article from Barbara Webb: "Animals versus animats: or why not model the real iguana", where she compares artificial models and real animals or artificial systems exactly copying the biological systems.

So we decided to use as the name of the group something less controversial: Cognitive modeling and bio-inspired robotics.

Nice, nice, nice. Haven't started yet and so nice discussion. Looking forward:-).

How have I decided to start this blog

It is quite a long story. Having nearly no time one could be curious why I decided to write a blog. And will this blog have more than this one contribution? And why I write in English eventhough my English is terrible?

Ok, ok. Lets start. I'm a PhD. student and have also a baby (1 year old girl). After master degree I haven't been sure whether I want to continue to study or start working. 5 months on the maternity leave decided instead of me. I have chosen school. But I decided to switch the theme and instead of physics do something more interesting for me - cognitive science. I had only very superficial knowledge of this field so I spent half year buried under books and I have tried to fill in the gaps in my education. I haven't finished this part yet:-)

But now the other part of my PhD. studies starts. I have to do some experiments, decide what I'll be focusing on, implement methods, algorithms and so on. I think that it could be nice to have some reminder of my progresses and work. Have some notepad where I'll try to write what are the most interesting issues for me by now, what are the problems of the models and so on and so on.

Another reason is that we are starting with new lab - Incognite (Cognitive modeling and bio-inspired robotics) and it is something like a milestone in Czech republic. There isn't any cognitive modeling group in Czech republic yet and even no department of Cognitive science. So maybe this is the first step to the new department.

We'll see.

I can't promise that I will write more than this contribution. But I'll try.
English isn't my cup of tea but I think that it is important when we start in Czech republic with cognitive science to have information in English to ease the cooperation. So I can only promise I'll try my best. Hope you'll understand.