I found that TemporalMemory runs slower and slower while training. Eventually becoming so slow that it is impartial to use. For example, taking 10 seconds to infer 1000 times after extensive training. At least 100 times slower than initially. Is there a solution?

I’d be interested in hearing what the bottleneck was. Perhaps, at the code level, there’ll be a target for reasonable parallelisation if it make sense. Very slowly moving towards a Pony implementation. If anyone wants to join, welcome .

I found that I can replicated the problem faster by sending random SDRs into a TM. Since sending random SDRs causes a lot of boosting. My guess is that there’s too much useless distal connections in the TM (Weight around 0, etc). Segments trimming seems to be a possible solution. And parallelizing …

[image] d-led: Very slowly moving towards a Pony implementation. If anyone wants to join, welcome . Behavior based asynchronous actor-model language? https://tutorial.ponylang.io/types/actors.html Dmitry, I’m in! The language sounds as good or better than Visual Basic, which I still progra…

@Gary_Gaulin very glad to hear! Visual Studio Code has very good syntax support. The resulting binaries are C++ compatible. On windows one can simply debug Pony binaries with Visual Studio. On Windows , the Visual C++ SDK must be installed. On other platforms it’s even easier.

I have been studying. With this link everyone is right away ready to start coding! https://playground.ponylang.io/ For an experiment we now only need easy sample code like your encoder example, to copy from a reply you post in this forum into the Pony Playground. One of the biggest problems in op…

Yes, the problem is likely that there are too many distal segments / synapses. There is no trimming going on as new patterns are learned. There is a way to counter this, but it is deep inside the Nupic code. What you would do is adjust logic within the TM so that anytime new distal synapses are cre…

[image] rhyolight: Yes, the problem is likely that there are too many distal segments / synapses. There is no trimming going on as new patterns are learned. There is a way to counter this, but it is deep inside the Nupic code. What you would do is adjust logic within the TM so that anytime new …

The code that needs changing is not in the TM (and we are not talking about the TP or “backtracking TM” at all here). The code that needs changing is in Cells4.cpp. We think the right place to make this change is within Cells4.cpp::adaptSegment , which is called by the TM to add more synapses. New f…

[image] rhyolight: e think the right place to make this change is within Cells4.cpp::adaptSegment , which is called by the TM to add more synapses That’s why I’ve asked about TM (Connections) vs. TP (Cells4, Segments). Cells4 is considered obsoleted by TM and unused (or something changed?) S…

TemporalMemory running very slow after long training

Engineering

d-led December 26, 2018, 10:30am 11

Let’s continue the Pony discussion in a separate thread: Concurrent HTM experiment in Pony: htm.pony

Topic		Replies	Views
Suggest change to Sequence Memory algorithm NuPIC sequence-memory	13	963	May 15, 2019
My analysis on why Temporal Memory prediction doesn't work on sequential data Numenta Theory sequence-memory	58	7698	February 2, 2020
The Principle of Temporal Memory Numenta Theory	21	867	April 25, 2021
Some details murky on temporal implementation Engineering	10	1411	September 6, 2017
Project to compare mraptor's bbHTM to biology Engineering	21	2158	June 22, 2016

TemporalMemory running very slow after long training

Related topics