[quote="Osaulenko_Viacheslav, post:5, topic:3000, full:true"] You can add nonbinary weights and nonbinary level of cell activation. Then different predictions will have different levels of activation. So, you will be able to feed not a union of predictions but only the most likely(more active). This can solve the problem [/quote]
[quote="Paul_Lamb, post:6, topic:3000"] This can almost be done with the current artifacts from the TM algorithm, by scoring number of distal synapses and their permanence to generate a non-binary SDR. It might require a global decay rate to be added to be used as a tie-breaker in cases where two paths are statistically equally likely to occur though. [/quote] Hi @bkutt, I have tried what was proposed above in one of the previous architectures that I worked on. Almost everytime it did not converge onto an actual activation that happened as @jakebruce said. It contained bits and pieces from multiple activations which was very hard to utilize in a meaningful way. So I went even further by creating a circular loop of two layers (reciprocal connections in some sense) in order to extract the dominant actual activation (an activation that happened) from this sparse union that contained bits and pieces from separate states. At the time I believed this was how basal ganglia resolved conflicting activations from a union of predictions (Cortex->Striatum->Gpe/Gpi->Gpi->Thalamus->Cortex): Lets say you have A and B layers that **only have spatial pooler**. Layer B classifies Layer A by taking its columnar/neural activation as input. In turn, Layer A takes input from B's columnar/neural activation. So if you activate some union activation in A and let the circular flow continue, it converges onto an actual state that happened previously because of the merits of SP algorithm. It worked in terms of extracting the dominant real activation but it solved the wrong problem for me which helped me understand a more fundamental problem about the architecture. --- [Visit Topic](https://discourse.numenta.org/t/getting-high-order-predictions-of-cellular-activations/3000/9) or reply to this email to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discourse.numenta.org/email/unsubscribe/3427024000f67e7bf5bed1825efb07e9f64cb282eb12bedcd8dc8f2da3cf6fe7).