An old discussion in the HTM forum I like to get back to once in a while.
It started like this:
“Assuming human beings at their most basic are driven by the need to reduce the level of surprise in the world, meaning prediction error, and that the physical translation of that is a mechanism to build a model of the world, whose convergence engine is the minimization of the energy spent in surprises, that the brain is that model and that its plasticity is the mechanism to reach the lowest average energy consumption in time, what would be, from all the optimization algorithms out there, the one that would best model computationally the dynamics of neuronal plasticity ? Did nature decide to implement gradient descent ? Seems ‘too mathematical’! ”
It continues here.
Origami Tree 