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 Becerrahttps://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/ > >> > > >> > > >> > > >
