90,000 frame test on new machine

Posted: April 4, 2014 at 5:03 pm

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) after ~90,000 frames:

perceptsFollowing are some frames notable selected from the test: (a mix of perception, dreaming and mind-wandering)

shortlist16 shortlist13 shortlist11 shortlist7 shortlist1

Here is the debug log from the test:

supermicro_84990.debug

Spikes in rendering are due to over activation of percepts due to predictor output. Early on many percepts (thousands) can be activated before the network is sufficiently trained. The fix was to limit the number of percepts rendered to 300, if more than that many are activated, they are not rendered.