First of all, I hope it’s appropriate to post this here - let me know if it should go elsewhere. I’m using htm.js in a hobby project I’m working on, and seeing something I think might be a bug. I noticed the behaviour in my implementation, but eventually found I can reproduce it in the piano demo. …

Sure I’ll take a look and see if there is a bug.

Ah, yes, you have encountered the “repeating inputs” problem with HTM. What happens is it is not learning a sequence of “A repeating”, but instead it is learning “A’A’‘A’’‘A’’’‘A’’’’’…” When it reaches the end of the long sequence that it has learned, (A’’’’’ in the above example), there is no pre…

I noticed this as well, it doesn’t matter if you hit a single key or if you hit a recurring pattern you will notice the bursting happening gradually, which i think is expected

I’m working on a strategy to solve this problem using a temporal pooling layer. A while back I talked about the basic strategy here . Sorry for the slow progress on this (I have lots of competing interests right now LOL)

@jimmyw You’ve found the main weakness of the TM. More thoughts, including the piano demo :

[image] rhyolight: the piano demo Uh oh. Just realized that is still an old version which has a bug (that is why it stabilizes eventually). I’ll update the demos with latest code when I get home this evening.

Thanks for the discussion (and the live-streamed badge presentation!). I’m surprised I’ve never seen this before but it totally makes sense. I guess there must be something to mitigate this effect in the anomaly detection tools like grok, or maybe it’s less of an issue in a noisier signal? When I l…

[image] jimmyw: I guess there must be something to mitigate this effect Yes, it is called BackTrackingTM. you can find it alongside the newer and more biologically accurate TemporalMemory algorithms. Most scalar anomaly detection models are using it.

[image] jimmyw: I guess there must be something to mitigate this effect You also have the option to use the connect-to-all method (Grow synapse from a predictive cell to all previously active cell, not just the selected active cell.). It forces TM to learn A-A-A instead of A-A’-A’’ unless the…

[image] Paul_Lamb: I’ll update the demos with latest code when I get home this evening Updated. Might need a clean refresh if browser cashed the old .js files. [image] marty1885: You also have the option to use the connect-to-all method (Grow synapse from a predictive cell to all previo…

Unusual prediction behaviour in htm.js

Engineering

Topic		Replies	Views
Exploring the "Repeating Inputs" problem Tangential Theories temporal-memory	36	3649	February 2, 2020
HTM is so much more than show tunes Numenta Theory	12	1346	March 15, 2018
Another HTM test implementation Engineering	18	1764	April 24, 2017
My analysis on why Temporal Memory prediction doesn't work on sequential data Numenta Theory sequence-memory	58	7699	February 2, 2020
TemporalMemory for prediction Engineering question	35	1943	September 24, 2019

Unusual prediction behaviour in htm.js

Related topics