David, I guess what Fergal is saying is that the CLA itself does only one step prediction. The OPF which is a framework that uses the CLA. Provides support for multi step predictions. Basically its doing mutiple predictions one step at a time. For Eg: Predict 1 step way, predict 2 step away, predict 3 step away .... and then repeat for the next input value.
Chandan On Thu, Mar 5, 2015 at 2:09 PM, David Wood <[email protected]> wrote: > Hi Fergal, > > I’m a bit confused by your answer. Is there no way using NuPIC to estimate > multi-step predictions? > > Regards, > Dave > -- > http://about.me/david_wood > > > > On Mar 5, 2015, at 15:49, Fergal Byrne <[email protected]> > wrote: > > Hi Michael, > > The region itself always just predicts one step ahead. You can connect a > region with code (most of it in OPF) which will remember what happens N > steps ahead of a timestep, but this is just a histogram record (associating > a cell's activation with an input field value) of what is likely to come up > after N steps. This is what is used if you specify multi-step predictions. > > Ignore the multi-step stuff in the White Paper. It's wrong, and has been > abandoned. CLA on its own just does a single timestep prediction, and this > is what also happens in neocortex. > > Regards, > > Fergal Byrne > > > On Thu, Mar 5, 2015 at 12:38 AM, cogmission <[email protected]> > wrote: > >> Oh the Prediction code is in CLAClassifier and the Anomaly code does the >> running total of the meta qualities... >> >> On Wed, Mar 4, 2015 at 6:36 PM, cogmission <[email protected]> >> wrote: >> >>> Hi Michael, >>> >>> Afaik, the "Anomaly" class is what you are looking for, just that it >>> tracks the moving average of accuracy or maybe the inverse (anomaly). You >>> could in any case have a look at that code to see if it either does what >>> you are looking for or can be "adapted" to do more of what you're looking >>> for. >>> >>> Also afaik, the steps will "overwrite" when that point in the cycle is >>> reached again (so every 500 steps a new prediction quality is estimated - >>> if 500-steps is one of the step configurations). >>> >>> Correct me if I'm wrong someone? >>> >>> David >>> >>> On Wed, Mar 4, 2015 at 6:21 PM, Michael Roy Ames via nupic < >>> [email protected]> wrote: >>> >>>> >>>> >>>> ---------- Forwarded message ---------- >>>> From: Michael Roy Ames <[email protected]> >>>> To: NuPIC Mailing List <[email protected]> >>>> Cc: >>>> Date: Wed, 04 Mar 2015 16:08:38 -0800 >>>> Subject: Prediction. Several steps. Future or past. >>>> NuPIC list: >>>> >>>> "Predictions in an HTM region can be for several time steps into the >>>> future" - according to the HTM White paper. >>>> >>>> Question 1: Is there a NuPIC code that does prediction for the next n >>>> time steps? >>>> >>>> Question 2: Is there NuPIC code that keeps activation history such >>>> that one could access the last 15 or 20 sets of active cells? >>>> >>>> I'm interested in making NuPIC learn and recognize temporal sequences >>>> of data, and want to limit the amount of additional code I have to write to >>>> get this done. So, I'd rather use existing NuPIC functionality that works >>>> instead of writing algorithm that might duplicate something already in >>>> place. The sequences may be long (500 steps) or short (20 steps). The >>>> one-step predictions I've found in NuPIC examples need extra code to be >>>> written to 'remember' the predictions and how many predictions in-a-row >>>> have been correct, each additional successful prediction lending greater >>>> confidence to the data recognition. >>>> >>>> Question 3: Is there code that does this already (successful prediction >>>> tracking), or will I have to write it? >>>> >>>> MRA >>>> >>>> >>>> >>>> >>>> >>> >>> >>> -- >>> *We find it hard to hear what another is saying because of how loudly >>> "who one is", speaks...* >>> >> >> >> >> -- >> *We find it hard to hear what another is saying because of how loudly >> "who one is", speaks...* >> > > > > -- > > Fergal Byrne, Brenter IT > > http://inbits.com - Better Living through Thoughtful Technology > http://ie.linkedin.com/in/fergbyrne/ - https://github.com/fergalbyrne > > Founder of Clortex: HTM in Clojure - > https://github.com/nupic-community/clortex > > Author, Real Machine Intelligence with Clortex and NuPIC > Read for free or buy the book at https://leanpub.com/realsmartmachines > > Speaking on Clortex and HTM/CLA at euroClojure Krakow, June 2014: > http://euroclojure.com/2014/ > and at LambdaJam Chicago, July 2014: http://www.lambdajam.com > > e:[email protected] t:+353 83 4214179 > Join the quest for Machine Intelligence at http://numenta.org > Formerly of Adnet [email protected] http://www.adnet.ie > > >
