Clearly - in this forum, we take the answer in the affirmative!
I think this Paper speaks directly to the theoretical underpinnings of HTM theory.
Fristen talks of the difference between predictions and perceptions (I call it surprise) as the error signal that is minimized by training. You learn surprising things - exactly what an anomaly is.
Some people have expressed some reserve as the underpinnings of HTM can’t be quantified. Clearly, the variational free energy is measurable & calculable and mathematically tractable. Has this ever been applied to the HTM canon and I just missed it?
I am very interested and have the same question. I am trying to collaborate with a Faculty in the Statistics department at my university to better understand mathematics behind Friston’s models, and I am actively working on some research with Monty. My intuition tells me that HTM is the way to link the works of Karl Friston to Monty. The question I still have is how…