Twitter | Pretraživanje | |
michael_nielsen
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!
Reply Retweet Označi sa "sviđa mi se" More
michael_nielsen 16. sij
Odgovor korisniku/ci @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.
Reply Retweet Označi sa "sviđa mi se"
michael_nielsen 16. sij
Odgovor korisniku/ci @michael_nielsen
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: I have trouble believing this works, but, well, you can read the paper yourself.
Reply Retweet Označi sa "sviđa mi se"
José Luis Ricón (Artir) 16. sij
Odgovor korisniku/ci @michael_nielsen
An analogy I use when learning a new domain is that learning from just one place may lead to overfitting, and it's good to see the context presented in different ways, linked to different things each time
Reply Retweet Označi sa "sviđa mi se"
José Luis Ricón (Artir) 16. sij
Odgovor korisniku/ci @michael_nielsen
Also helps to get a sense of how robust the literature is and how much debate is there.
Reply Retweet Označi sa "sviđa mi se"
POLAR - Personal knowledge repository 16. sij
Odgovor korisniku/ci @michael_nielsen
... and once I got the supervised learning metaphor I was addicted and that's why I started building Polar. We now have our own implementation of SM2 and sync with and I think the fully integrated environment is really addictive.
Reply Retweet Označi sa "sviđa mi se"
Tom Bielecki 16. sij
Odgovor korisniku/ci @getpolarized @michael_nielsen
Will Polar someday have BiDirectional Links and Indented lists/references like Roam Research? I really want to go back to Polar for SRS but Roam's workflow fits my brain better
Reply Retweet Označi sa "sviđa mi se"
Emaad Manzoor 17. sij
Odgovor korisniku/ci @michael_nielsen @btabibian i 2 ostali
You may find the Memorize project ( ) by and team relevant. They have an accompanying paper in PNAS '18: "Enhancing human learning via spaced repetition optimization"
Reply Retweet Označi sa "sviđa mi se"
POLAR - Personal knowledge repository 16. sij
Odgovor korisniku/ci @michael_nielsen
The analogy of supervised learning and spaced repetition I think is dead on. I've been referring to Polar as a "cognitive prosthetic". My background is partly in machine learning so when I got into I immediately realized it was supervised learning for humans.
Reply Retweet Označi sa "sviđa mi se"
Phil Mohun 16. sij
Odgovor korisniku/ci @michael_nielsen
What's the best tool for spaced repetition? I've tried the ANKI app, but it's clunky. Any good implementations?
Reply Retweet Označi sa "sviđa mi se"
Tom Bielecki 16. sij
Odgovor korisniku/ci @philmohun @michael_nielsen
Have you tried Quizlet? I think it has an underlying SRS algorithm, and really user friendly
Reply Retweet Označi sa "sviđa mi se"