|
@michael_nielsen | |||||
|
In the next essay we are, in fact, doing something much like adding noise to the questions (or, at least, variation) to help improve generalization.
|
||||||
|
||||||
|
michael_nielsen
@michael_nielsen
|
16. sij |
|
Striking analogy between the mnemonic medium and supervised learning. Makes me think about analogies to things done in supervised learning: adding noise to the data (questions) to improve generalization; changing the loss function (overall scoring), etc. Fun to think about! twitter.com/mlpowered/stat…
|
||
|
|
||
|
michael_nielsen
@michael_nielsen
|
16. sij |
|
Incidentally, a very amusing instance of this idea is sans forgetica, a typeface designed to improve retention because it's so damned difficult to read: en.wikipedia.org/wiki/Sans_forg… I have trouble believing this works, but, well, you can read the paper yourself. pic.twitter.com/Nr7R5sNfWX
|
||
|
|
||
|
Evan Cater
@Evan_ec
|
16. sij |
|
Hey Michael, are you guys working towards an open source or other framework for creating / posting / experimenting with mnemonic mediums? I know some people interested in creating their own pedagogical resources with this paradigm.
|
||
|
|
||
|
michael_nielsen
@michael_nielsen
|
16. sij |
|
Yes. We're starting to work toward a platform; of course, we're also still working out what the medium wants to be (major improvements coming in the next essay).
|
||
|
|
||
|
Paul Simeon
@PESimeon
|
16. sij |
|
This should be great, because one problem I have with Anki is that I can recognize some cards and know the answer without really thinking about it. This is especially true with cards with images.
|
||
|
|
||
|
Martin Kavalar
@mkvlr
|
16. sij |
|
Are you also working on an executable book?
|
||
|
|
||
|
Giacomo Randazzo
@RAN3000
|
17. sij |
|
My 2 cents.
twitter.com/RAN3000/status…
|
||
|
|
||