The primary hurdle is the number of "activity types" practice can come from. Simply reviewing material isn't sufficient for learning and so we need more engaging practice as well. Also, similar to how "all students are different", topics encompass a large number of subskills that need to be trained and not all activity types target those skills. Also, "learning" something is quite complex - is simple repetition of the fact sufficient, or do we need the ability to apply the skill?
Its actually research we're doing at NC State. At present, we understand spaced, deliberate practice is beneficial [1] but students will largely reject AI recommendations to complete lower-level practice [2]. So our current methods are to develop a system that maintains an "instructor in the loop" to create tailored training regimens (my terminology for it), similar to how a coach builds regimens for athletes. The hope is that if we can analyze how instructors made their recommendations, we could then design AI to mirror the decisions.
Thank you. I suppose I was downvoted, hiding your careful response, because I appeared to be pitching a product. I was attempting a precise analogy, I had nothing to gain from the promotion. I was robbed on BART recently, and my judgment is off.
I've relied heavily on spaced practice for learning languages for travel. There are two phases to that experience: Study, where one takes in as much as possible, then real world practice without further study. I find myself wishing I'd memorized a play for the first phase, to access faster than a phrase book on the ground, with lots of pathway shortening while I travel. Learning models tend to assume learning is single-phased, though even more academic learning is two phased: acquire, then later apply.
That's actually where the inspiration of my work comes in. Outside of academia, I also teach martial arts, where practice is often structured as "present" -> "practice" -> "introduce new element" -> "practice" -> "introduce new element" -> repeat. The hope is the training regimens will help model that a little.
Another note when I think about learning is how, as adults, we are resistant to many of the techniques we give children. Thinking about Sesame Street, think about how much a skit/song will focus solely on something like the number 3. Simplified language, repetition, and enjoyable content are things adults think are "beneath them" despite the fact they work, just not as "fast" as adults want.
Its actually research we're doing at NC State. At present, we understand spaced, deliberate practice is beneficial [1] but students will largely reject AI recommendations to complete lower-level practice [2]. So our current methods are to develop a system that maintains an "instructor in the loop" to create tailored training regimens (my terminology for it), similar to how a coach builds regimens for athletes. The hope is that if we can analyze how instructors made their recommendations, we could then design AI to mirror the decisions.
[1] https://dl.acm.org/doi/pdf/10.1145/3373165.3373177
[2] https://repository.lib.ncsu.edu/bitstream/handle/1840.20/398...