Frank,

I like how you are discussing backpropagation, stochastic gradient descent (never heard of these terms before), and adjusting weights. I’m assuming this is the process or constructs of designing AI algorithms.  Members in my grade band were trying to get at and understand this process.  I think you raise good points.  I would like to know more, so that I can know how much teachers need to know to convey the overall concept to students, without digging to far in.

Sent from my iPhone

> On Jul 28, 2019, at 9:23 AM, Frank Zeng <xxxxxx@aafie.org> wrote:
>
> But they should understand what backpropagation and stochastic gradient descent are doing —— “trying to adjust weights to minimize the errors”.