Asymmetric confidence when predicting a symmetric signal

[rhyolight]

@Bitking

Granted - this is a lower brain function but I would not think it out of line to add a mechanism to do this with canonical HTM.

I thought you generally against modeling too much in the canonical cortical circuit. This would be adding more to that representation that you admit is not there in the brain.

@pulinagrawal

In summary, with ‘py’ implementation predictionConfidence behaves as expected, i.e having generally 100% confidence in predicting a very predictable signal.

@pulinagrawal Well done! I really appreciate you taking the time and effort it took to present this.

@PhilGoddard

That’s very interesting.

That is exactly what I thought. I’m not sure what to make of this.

[Bitking]

@rhyolight

I thought you generally against modeling too much in the canonical cortical circuit. This would be adding more to that representation that you admit is not there in the brain.

Well, you could do it right and bring in the sub-cortical drivers of these repetitive actions.
I would be a of a fan of that but it does seem a long way away from where we are at the moment.
Adding a small driver to abstract the function for now seems like a reasonable compromise.