Aesthetic Variation

I started dumping the most recent time (frame number) each percept was clustered to get a sense of the range of time encapsulated by the percepts. Turns out that the range is very small, in the last test the difference between the min and max times was 29, which represents only about one minute of real-time. So even if the predictor was making broad predictions, the precepts would not represent them! My intuition about this is that there are not enough percepts to represent the complexity of a real-world scene for more than a short period of time. Of course since all new percepts are clustered, this makes sense. Not doing so would mean blindness to the novel. Indeed since percepts are weighted clusters, so they hold more information than is represented in the time of the last clustering operation. Following is a composite of all the percepts after ~90,000 frames, which clearly appears to be fairly cohesive in time and lighting:


Dreams turn out to be quite boring, partially because the percepts don’t change due to the lack of external stimulus. In a real-world urban setting perhaps the kind of darkness that leads to dreaming will be rare, and the system will fade in and out of waking and mind-wandering. Since mind-wandering is punctuated by periods of waking, there is much more variation in the visual appearance of mind-wandering, as shown in the following examples: (Note the impossible combinations, where some images show percepts that are not contiguous in time.)

output-045976 output-033670 output-029594 output-025590