Why is HTM Ignored by Google DeepMind?

[Chris]

Really enjoying this discussion, and very useful to me as a relative newcomer to HTM. Thank you!

I just wanted to pick up on something that @Charles_Rosenbauer mentioned in an earlier post:

@Charles_Rosenbauer

That said, there is another big difference between HTM and DL; reinforcement learning. Currently, if you want to train a DL network to do a useful task, it’s very easy. If you want to train HTM to do the same thing, you have very few options. I think what HTM needs is some form of reinforcement learning.

Does anyone have any thoughts about this, or how we might approach a solution?

… that is, in addition to this post by @Charles_Rosenbauer which deals with some of the biological aspects.