Random vs Averaged Seed Structure on Top Row

Posted: April 29, 2016 at 8:50 am

Seed data on top row is random:

Seed data on top row is calculated from the average of the segments in each column:

I wanted to follow up on some of the conceptual aspects I touched on in my previous post. When I started my Masters degree I was really interested in how I could create a computational process that was not random nor a perfect reflection of my intention nor the outside world. In general, I try to use randomness as sparingly as possible. In my Masters project I, as best as I can recall, did not use any randomness at all, making the system deterministic. Since it used images from its environment (that was constantly changing) it was unpredictable, and yet deterministic.

I’m still very interested in the idea of a Tabula rasa when it comes to cognition. I don’t deny that we are born with particular mechanisms in place that allow us to make some sense of reality, but as those mechanisms themselves develop in a process. It could even be argued that those ‘innate’ mechanisms are actually the result of another learning process operating on an evolutionary scale. I got into computational creativity and AI because I was interested in origination; how do you make a structure that is not just random nor a copy of what already exists? I think the answer is that every structure is a copy of a structure that already exists. As each copy exists in a slightly different context than the ‘original’, those learning processes are augmented leading to changes in structure.

Lets says the panorama that is the basis of the image above original image is a proxy for reality. On the bottom row we have the results of a series of mechanisms that copy/measure the world within a context of constraints. As we move up the rows of the image the copying process is augmented by an increasingly destructive learning process. In the case of the previously posted image that fails to fill the image plane, the top row is a total absence of structure, and that absence is not easily transformed by the learning process into a copy of reality. The top row is a scaffolding that bootstraps the learning process. Do we start with a clean slate, or in an arbitrary state whose origin cannot be determined? I don’t think we begin with randomness that is slowly transformed into structure through a learning process. I think our initial mental structure is a copy itself, a copy with a long and complex history that is impossible to follow. Perhaps all randomness is. Our initial mental structure is a copy of reality, a copy meant to make copies of reality itself.

The top row, even as a metaphor for the most extreme imposition of cognitive structure on reality, is still is seeded by reality itself.