Hi Fergal, thanks for your advice. If I understand you, you mean to apply this to the "new sentence starts after reset" ? Because otherwise the flow is driven by the memory of CLA.
I will do that, if I dont find a better solution. (<= actually I think your SP-enhanced will cut it! ) The thing I'd prefer would be some "educated guess", so the sequences could make sense as they follow. Problem here is, the sequence of states is always "<RESET>, ??", so ?? is simply statistics of the most common first-letters. Do you have this student's result's, so we can compare CLA? Btw, I'd like to hear your intake on the randomization of undecidable states.. :) regards, Mark On Sun, Nov 17, 2013 at 4:47 PM, Fergal Byrne <[email protected]>wrote: > Hi Marek, > > This is great. One suggestion is to steal from one of Geoff Hinton's > students, who did exactly the same letter-by-letter prediction. What he did > was to take the predictions, let's say: > > d: 0.33 > t: 0.27 > e: 0.2 > f: 0.2 > > And use a random generator to decide which of these to give it next, in > proportion to their probabilities. So 1/3 of the time you give it a d etc. > > > > > On Sun, Nov 17, 2013 at 3:05 PM, Marek Otahal <[email protected]>wrote: > >> Here;s illustrative output on running a "xAAA. xBBB" dataset. >> >> ====== Repeat #100 ======= >> >> [991] x ==> BBB|x (0.50 | 0.50 | 0.50 | 1.00 | 1.00) >> <<<<<learning correctly >> [992] A ==> AA|xB (0.88 | 0.78 | 0.78 | 0.78 | 1.00) >> [993] A ==> A|xBB (0.92 | 0.81 | 0.81 | 0.89 | 1.00) >> [994] A ==> |xBBB (0.80 | 0.80 | 0.80 | 0.88 | 1.00) >> [995] | ==> xBBB| (1.00 | 0.92 | 0.92 | 0.92 | 1.00) >> DEBUG: Result of PyRegion::executeCommand : 'None' >> reset >> [996] x ==> AAA|x (0.50 | 0.50 | 0.50 | 1.00 | 1.00) >> <<<<<<learning correctly >> [997] B ==> BB|xA (0.94 | 0.89 | 0.89 | 0.89 | 1.00) >> [998] B ==> B|xAA (0.91 | 0.85 | 0.85 | 0.94 | 1.00) >> [999] B ==> |xAAA (0.85 | 0.85 | 0.85 | 0.94 | 1.00) >> [1000] | ==> xAAA| (1.00 | 0.91 | 0.91 | 0.91 | 1.00) >> DEBUG: Result of PyRegion::executeCommand : 'None' >> reset >> ========================================== >> Welcome young adventurer, let me tell you a story! >> Enter story start (QUIT to go to work): x >> x x B B B <<<<interpretation is always same!! >> >> >> x B B B >> >> Enter story start (QUIT to go to work): x >> x x B B B >> >> >> x B B B >> >> Enter story start (QUIT to go to work): x >> x x B B B >> >> >> >> >> On Sun, Nov 17, 2013 at 4:01 PM, Marek Otahal <[email protected]>wrote: >> >>> I've added an "interactive" feature to Chetan's Linguist >>> https://github.com/chetan51/linguist - a story teller mode. >>> >>> It will (more or less) memorize the given text and then let you type >>> starting words (ie "So he ") and follow up on its own to complete the >>> sentence(s). >>> >>> --------------------------------- >>> Yet there's a problem. >>> >>> I'll describe the project briefly, it uses TP to learn texts as a >>> sequence(s) of letters. >>> >>> First it used to memorize whole text as one long sequence, this worked >>> for smaller datasets, but for bigger, the accuracy went down quickly. >>> >>> I decided to simplify and separate text to separate sequences and reset >>> the sequence memory of the temporal pooler at the end of each sentence. >>> This greatly improved prediction probabilities as sequences are much >>> shorter (avg sentence lenght (+-30chars) vs dataset len (hundreds - >>> thousands chars)). >>> >>> The problem is, after the first end of sequence, there's no "flow" (I >>> know, I've called a reset(), what could I expect ;) ), so a state with >>> highest statistical probability is selected (always the same!) >>> >>> example dataset: " >>> How are you? >>> I'm fine. >>> I'm tired. >>> Yayyyyy!" >>> >>> So when you start "Ho"..it'll correctly follow.."w are you?" "I'm fine" >>> "I'm fine" "I'm fine"...forever. >>> >>> The "I'm fine" is fine :) as from a new state it's the most probable >>> choice (2 out of 4). But it doesn't look good. >>> >>> I;ve come with 2 solutions: >>> # Idea1: >>> after seq reset in the generation mode, randomly generate the first >>> char manually, feed it to TP and let it follow... >>> should work: OK, principle: so-so. >>> >>> #Idea2: >>> even though I trained with a reset (=new unknown state) after each >>> sentence end, can I now somehow keep the flow spanning over more sentences? >>> >>> >>> Last but not least, the bug! >>> The bug is in (CLA)model's result.inferences['prediction'] >>> By definition, this field should return the most probable state from the >>> inference. But what if there are two+ most probable states? I believe we >>> should go random. >>> >>> While for debuging the fixt order is convenient, the random order seems >>> natural. I believe it would fix my problem with repetitive "Im fine" above >>> too. (kindof) >>> >>> Proposed solution, if you agree, we;ll add init() parameter debug=False >>> which will keep the fixed ordering if needed, and by default, do random on >>> same probable states. >>> >>> Thanks for reading :) >>> mark >>> -- >>> Marek Otahal :o) >>> >> >> >> >> -- >> Marek Otahal :o) >> >> _______________________________________________ >> nupic mailing list >> [email protected] >> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org >> >> > > > -- > > Fergal Byrne, Brenter IT > > <http://www.examsupport.ie>http://inbits.com - Better Living through > Thoughtful Technology > > e:[email protected] t:+353 83 4214179 > Formerly of Adnet [email protected] http://www.adnet.ie > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > -- Marek Otahal :o)
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
