I’ve a question on the SP. If I run a sequence A,B,C through a SP, would it be fair to say that the activeColumns I get after sp.compute for C would include the learning of both A and B with learning = True? If yes, then would it be ok to say this output SDR represents the sequence ABC?
1 Like
No, you are confusing spatial pooling with temporal memory. The SP does not do sequence memory. Have you seen all the HTM School videos?