Clustering and Performance Test (50 clusters, 20,000 frames)
The spiking clustering time has been solved! The change in the code was to mark both clusters and scratch units for removal after a merge, whereas previously only clusters would be marked. This test...
View ArticleClustering Test 8 (45,000 frames, 2000BG, 1000FG)
This is the first long term test covering material over an approximately 12 hour period, shown in the following plot. In this case there are 2000 foreground clusters and 1000 background clusters. The...
View ArticleMeeting with AI Specialists
I had a valuable two hour+ meeting with a two fellow students specializing in AI (Omid Alemi: Multi-Agent Systems, Graeme McCaig: Deep Learning) to discuss how RL could be applied in this project, and...
View ArticleClustering Test 9 (87,800 frames, 2000BG, 1000FG)
This is the first test showing an entire day-night cycle (approximately 24 hours). As expected, the plots show the number of percepts and processing time (segmentation + clustering) drops down to...
View ArticleStates and Prediction
In order to start working on prediction and learning for DM3, I’ve starting dumping some state data to see what it looks like over time. The idea is that learning will only happen once the max clusters...
View ArticleState Vector Update
Whether I end up using an MLP, RL, or some other ML method, the representation of the clusters must be stable. That is, the index that represents percept A should represent percept A in all frames,...
View ArticleClustering Update
Following are images that represent the learning of percepts over time. Each pixel represents the mean colour of a percept at a particular time. The identity of the percept is the Y axis, while the X...
View ArticleThreading Test
After quite some frustration I have managed to move the segmentation and clustering code into a separate thread. This thread runs as fast as possible, and the main rendering process checks in on the...
View Article~150,000 frame test with live camera
In preparing for the exhibition of a prototype of the system for Creativity and Cognition, I’ve been running the system with a live camera input. The good news is that the system is looking...
View ArticleCreativity and Cognition Approaching Fast!
I have been hurriedly attempting to fix some of these memory leaks before exhibition at the Creativity and Cognition conference happening next week. In lieu of any significant development progress,...
View ArticleAttention and Prediction
After watching this video, I was inspired to think about attention in relation to the Integrative Theory that has been developed during this research project. There is something very interesting in the...
View ArticlePost Creativity and Cognition
I am back in town for almost a week and still struggling with jet-lag. The conference went well, and I will post my paper as soon as the proceedings are on the ACM website. The papers in the conference...
View ArticleMemory Leak (Segmentation)
A test over this weekend showed that there is no memory leak or CPU time spikes in any of the segmentation code (the y axis is rss in megabytes): CPU time is constant over this test, and we can see...
View ArticleClustering Memory Leak Solved!
After confirming no leaks in the segmentation code I reran the clustering unit test. Even over 1000 frames, this clustering code showed a significant leak: (The black line is a linear model fitted to...
View ArticleClustering Memory Leak (not solved)
Further testing has shown that there is still a leak in the clustering code, but I can’t figure out where it is. It does seem that cv::Mat is somehow at the centre of this issue though. I had...
View ArticleMachine Learning Progress? (non-recurrent MLP)
I’ve put my leaking code problems aside for now to continue working on the project, the next phase being the ML stuff. So I’m now using FANN because while OpenNN was nicer, more complete and active, it...
View ArticleDream Simulation (failure)
After training the MLP, I thought I should try running it in feedback mode to see if it would actually be predictive. It is not. There are some shifts in input patterns at the start of the dream, but...
View ArticleData Stability Over Time
After meeting with Philippe, we decided that the static dreams could be due to the variation over time in the data-set being “seen” as noise in the data by the ANN, which is attempting to generalize...
View ArticleDream Simulation (Periodic)
I ran a test training the MLP with data filtered such that at least one cluster must change state between subsequent frames. This time, the result is a periodic dream that does not stabilize over...
View ArticleMemory leak solved?
After almost two months, and seeking the help of quite a number of people who know a lot more about C++ than me, the problem I’ve been facing with the memory leak has been (at least partially)...
View Article