Hello,
I’m glad that you succeded in using the htm.core framework for your reseach. I put a lot of work into that project.
And it’s nice to see more rigourous verification of the HTM algorithm and all of its variations.
I also came up with another form of homeostatic control, and I’d love to see your analysis of it. I wrote about my experiments in more depth here: https://discourse.numenta.org/t/synapse-competition/5957/15?u=dmac My conclusion was as follows:
Normally all of the synapses in the spatial pooler have a weight of either 0 or 1. Instead, you should divide the weight of each synapse by the total number of connected synapses to the postsynaptic cell.
So, instead of comparing cells based on the total number of synaptic inputs, this compares cells based on the fraction of their connected synapses that are active. The range of inputs to a cell is now in the range [0, 1]. Now cells can compete to activate on a level playing field even if they have different numbers of connected synapses, whereas previously cells with more synapses would have an advantage over cells with fewer synapses.
This is a technique that I’ve seen done by other similar NN models.
Sincerely