Mean Shift Segmentation – Revisited
In the last post I talked about a different segmentation approach rather than trying to figure out why the FloodFill() operation was using more and more time (Eventually getting to over 200 seconds per...
View Article150,000 frames, Single epoch sequential training
After the previous tests I’ve gotten a better sense of the prediction problem. We realized there may not be enough data in my previous tests to get sufficient training (corresponding to a few days of...
View ArticleUpdates to Segmentation and Clustering
After implementing the predictor in the main DM program, I had the chance to run the and them dump percepts to give some form to the ML generated output previously posted. The results were quite weak....
View Article30,000 frame test – Segmentation and Clustering
Over the weekend I ran a 30,000 frame test, thus far the longest test running the predictor and integrated segmentation and clustering system. The temporal instability has lead to many percepts ending...
View Article100,000 frame test – Segmentation and Clustering
This is the longest test in some time where the percepts are actually dumped to disk so we can take a look at them. Callgrind indicated that my inline weighting (just using the * operator on cv::Mats)...
View Article150,000 Frame Test – Segmentation and Clustering
After some tweaks of the segmentation and clustering code, it seems we have something that won’t turn to mud after a few days. Consider the image from the previous post as reference when considering...
View ArticleWork in Progress – Perceptual Rendering
I realized after so much work I have not been able to see how clusters behave over time. So I finally took a day to write a first crack at a rudimentary OpenGL renderer for DM3. Up to this point I was...
View Article~250,000 Frame Test
Now that it looks like segmentation and clustering are working, I’m starting to implement the system dynamics that will generate images in mind-wandering and dreaming. As a first step in this process I...
View ArticleArousal
In preparation for dreaming and mind-wandering states I was looking at the measures of system dynamics that could be used to trigger mind-wandering. At first I tried the number of clusters that changed...
View ArticleSystem Dynamics (84,990 frames)
Now that the prediction feedback mechanism and arousal have been written, I’ve been able to do some early tests to see what the system’s behaviour is like. Right now I’ve only been running short tests...
View ArticleEphemeral Percepts and Sparse Dreams
I’m currently running a long test of the longest contiguous part of the data-set, but in previous tests (with much shorter training periods) the dreams have been shown to be quite static. Following is...
View ArticleSparse Dreams Revisited
After the discussion in the previous post I took a look at the state data dumped by the program. While the waking and non-waking (dreaming and mind-wandering) states are clearly differentiable...
View ArticleNoncropped Percepts
I changed the percepUnit class so that percepts are stored at a fixed resolution (the full resolution of input frames). This way opencv does not try and reallocate any memory on merging percepts, and...
View ArticleMemory Leak Solved (for real this time)
While out of town I ran the new non-cropped code over the whole ~250,000 frame data-set. The results clearly show that keeping the percept images to a fixed size solves the memory leak problem....
View ArticleDensity of Dreams, Arousal and Training Samples
Now that all the system components have been implemented, I’ve finally had a chance to get a proper look at the system’s behaviour. Following are three images that show the display during perception,...
View ArticleAesthetic 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...
View ArticleSome examples images from last test
Some recent images generated by the system. This is a mix of perceptual and dreaming / mind-wandering processes. The perceptual images are generally brighter and more cohesive, as in they reflect a...
View ArticlePerformance of New Machine
Thanks to my supervisor I have a new faster shuttle to work with. The previous machine was almost 5 years old, and considering the heft of the computation involved in this project a faster machine goes...
View Article90,000 frame test on new machine
The first test on the new machine went quite well. The system is now storing 4000 percepts, and seems to be performing quite well. Following is a dump of all percepts (stacked on top of each other)...
View ArticleSynthetic Dataset
In order to deal with the problem of static dreams Philippe asked me to create a synthetic data set that has particular temporal properties. The idea is that we can use it to get a sense of both the...
View Article