Hi Roberto, Yes, those are called automatically. With most real data we have seen speed does slow down initially as it learns the patterns but the rate plateaus after a while. The default decrement value is sufficient to handle these noise cases. Pure random sequences are the worst case - you might need a higher permanence decrement value.
We have run models for months at a time, but in those cases we tend to feed in one data point every 5 minutes. What you are doing is a nice stress test of the system. Perhaps it will expose some problems that need to be fixed! --Subutai On Thu, Dec 3, 2015 at 8:06 PM, Roberto Becerra <[email protected]> wrote: > > Hi! and thanks all for your comments, > > So, to recap, it is the randomness of the input that makes the system > create more connections. There is a way to "Updates synapses on segment." > and "Strengthens active synapses; weakens inactive synapses" I wonder if > this is called automatically. I would think so, to avoid this clogging. > > Still my opinion on this is that all real data will have a fair amount of > noise/randomness, and so it seems like this decrease in execution speed > would be more like the norm. > > It looks like this is going deeper down the rabbit hole! I appreciate the > sharing of knowledge, now I will have to go into these readings. > > Cheers! > > Roberto Becerra > https://iobridger.wordpress.com/ > > > > > > Date: Thu, 3 Dec 2015 22:23:59 -0500 > > Subject: Re: Model Run Slowing Down > > From: [email protected] > > To: [email protected] > > > > > yes that is one of the documents I currently read. I have to be very > > careful because there were alot of stuff I missed on the first read, > > so I'm rereading. > > -------| http://ifni.co > > > > > > On Thu, Dec 3, 2015 at 5:22 PM, Matthew Taylor <[email protected]> wrote: > > > Have you read this yet? It should provide a very long-winded answer to > your > > > question about synapses. > > > > > > http://arxiv.org/pdf/1511.00083.pdf > > > > > > --------- > > > Matt Taylor > > > OS Community Flag-Bearer > > > Numenta > > > > > > On Thu, Dec 3, 2015 at 12:45 PM, mraptor <[email protected]> wrote: > > >> > > >> > > > >> The model keeps trying to learn sequences and is creating an > > >> increasing number of synapses and segments containing the new random > > >> transitions that it sees. > > >> > > > >> > > >> What is the mechanism/algorithm for creating/destroying segments ? And > > >> the "attachment" of synapses ! > > >> Couldn't find explanation for this process in the docs. > > >> > > >> thanks > > >> > > >> -------| http://ifni.co > > >> > > >> > > >> On Thu, Dec 3, 2015 at 2:25 PM, Subutai Ahmad <[email protected]> > wrote: > > >> > Roberto, > > >> > > > >> > This is not unexpected if you are feeding in random data all the > time. > > >> > The > > >> > model keeps trying to learn sequences and is creating an increasing > > >> > number > > >> > of synapses and segments containing the new random transitions that > it > > >> > sees. > > >> > If you feed in more predictable data (e.g. self.amplitude = > > >> > (self.amplitude > > >> > + 1)%200 ) you should not see such a large increase in time. If you > > >> > still > > >> > see a big increase with predictable data then there might indeed be > some > > >> > memory issue. > > >> > > > >> > --Subutai > > >> > > > >> > On Thu, Dec 3, 2015 at 9:34 AM, Roberto Becerra > > >> > <[email protected]> > > >> > wrote: > > >> >> > > >> >> Hi community! > > >> >> > > >> >> So, I have built a very simple script just to try the speed of > > >> >> execution > > >> >> of NuPIC, because I am seeing that it slows down a lot after a few > > >> >> hours of > > >> >> execution, I wonder if you have observed this or have any comments > on > > >> >> something weird I might be doing. The script goes like this: > > >> >> > > >> >> self.model = ModelFactory.create(model_params.MODEL_PARAMS) > > >> >> self.model.enableInference({'predictedField': 'binAmplitude'}) > > >> >> self.likelihood= AnomalyLikelihood() > > >> >> self.startTime = time.time() > > >> >> while True: > > >> >> self.amplitude = random.randint(0,200) > > >> >> self.result = self.model.run({"binAmplitude" : > > >> >> self.amplitude}) > > >> >> self.anomaly = self.result.inferences['anomalyScore'] > > >> >> self.likelihood = > > >> >> self.likelihood.anomalyProbability(self.amplitude, self.anomaly) > > >> >> print 'Loop Period: ' + format(time.time() - self.startTime) > > >> >> self.startTime = time.time() > > >> >> > > >> >> It is creating one model and running forever with random inputs. In > > >> >> the > > >> >> beginning the Loop Period is around 0.01 seconds, or 100 Hz, but as > > >> >> time > > >> >> goes on (I left it running over night) the period increased to > values > > >> >> that > > >> >> are not constant, but reaching up to 4 secods, 10 seconds or even > 128 > > >> >> seconds! > > >> >> > > >> >> I am running quite a limited computer, but I don´t think this is > the > > >> >> cause, maybe some memory leak? or resources that are available for > > >> >> python? > > >> >> > > >> >> OSX El Capitan (but it was happening in Yosemite as well) > > >> >> Mac Mini Intel Core 2 Duo 2.0GHz , A1283 2GB 250GB > > >> >> > > >> >> What do you think of this? Thanks! > > >> >> > > >> >> Roberto Becerra > > >> >> https://iobridger.wordpress.com/ > > >> > > > >> > > > >> > > > > > >
