Hey all, Got a few questions after going through Matt’s tutorials (very informative btw, thanks Matt!).
Why does prediction lag instead of lead until a large number of samples has been processed? I remember reading about that in the ML and it having something to do with HTM passing through observed values as-is when it can’t predict well. Can someone elaborate on that please both in terms of how its implemented and the rationale behind it? It tends to produce very misleading plots especially when the anomaly score isn’t usually high enough to indicate the pass-through events. Why is the timestamp included as an encoded field and passed to the network in the gym example? Is it processed in the same way as the consumption field or is it only used to align predictions with their corresponding inputs? For cases with uniform sampling (like the sine example), can we simply ignore that field and only encode the equivalent of the consumption field? Is there a relationship between anomaly score/anomaly likelihood and prediction error (= prediction - ground truth)? Or is the anomaly an indication of HTM’s confusion/certainty rather than its predictive accuracy? Thank you for any hints. Much appreciated :). best, Nick
