Background: In Numenta’s 2017 paper “how columns enable learning the structure of the world”, they described the output layer where stable representations of objects are formed, and they describe how the output layer cells can communicate via distal dendrites, with the goal of determining which of many possible objects they are sensing.
I hypothesis that the output layer’s distal dendrites could be implemented using a temporal memory.
I have not tested this idea, but i thought I would put it out here because other people have been discussing this topic.
One possible flaw with my hypothesis is that there is no competition amongst the distal dendrite activity. In numenta’s algorithm the cells can compete to activate on the basis of how many active distal segments they have.
One solution might be to implement a competition inside of the mini-columns of the TM.
IMO, I don’t think this is necessary. If we leverage what we’ve learned from vanilla HTM, we would set up the system such that predictions are always tested against reality. With that in mind, the driving input should always be derived from reality, allowing wrong predictions to be quickly eliminated via the TM algorithm.
What do you mean by output layer? Are you referring to the output of the temporal pooling algorithm? Or perhaps the more recent voting mechanism?
(references for background): the 2017 experiments reported in the “columns” paper used Numenta’s “column pooler” algorithm for the “output layer”. This has proximal segments connecting to (apical tiebreak) temporal memory output, and lateral segments for inter-column (cortical column) “voting”; CP distal segments are for intra-column connections. Column pooler output provided the input to TM apical segments.
HTM-scheme re-implemented the apical tiebreak temporal memory (“ATTM”) and column pooler algorithms and replicated Numenta’s figures 3B/C, showing faster convergence with 3 cortical columns voting on object representation.
I’m currently looking at extending ATTM to replace CP as the output layer.
@rogert i am interested in knowing what and why is the modification of yours from the original CP and ATTM for your improvement on object classification.
Could you please give me more information?
Your definitely correct for a single cortical area, but i worry that multiple areas could allow wrong answers to persist?
I might be thinking of it wrong, but I believe more CC’s would lead to faster convergence on the right answer, not slower. I think I actually have an old experiment using htm.js set up the way I described in this post. I’ll see if I can dig it up and post a link when I get back home from vacation next week.