search

plonerma / understanding-maml

An Interactive Introduction to Model-Agnostic Meta-Learning: Exploring MAML and its extensions
https://plonerma.github.io/understanding-maml/
1 stars 1 forks source link

How would a conclusion look like? #13

Closed plonerma closed 3 years ago

plonerma commented 3 years ago
plonerma commented 3 years ago

PR #14 contains a starting point

luis-mueller commented 3 years ago

Conclusion via b377133951b653faf52e92ea3f4b631338002463

luis-mueller commented 3 years ago

Making maml-tf2 public depends heavily on #11, maybe we should just close this one and move the maml-tf2 stuff together into #11?

plonerma commented 3 years ago

I added the task to #11 One thing I would also like to add to the comparison, is an empirical comparison (ie. accuracy numbers on omniglot and mini-imagenet as reported in the papers). I will close this issue once Im done with that.

plonerma commented 3 years ago

Before you leave: After letting your browser compute a bunch of meta-updates, you may want to cool it off and take a look at our computationally lightweight but not-to-miss further reading section.

Top-notch transition by the way! I like it :smile:

luis-mueller commented 3 years ago

One thing I would also like to add to the comparison, is an empirical comparison (ie. accuracy numbers on omniglot and mini-imagenet as reported in the papers).

Do you want to add screenshots or build your own table?

plonerma commented 3 years ago

I will just translate it into html. One method (MAML, FOMAML, REPTILE, iMAML) per row, and one or two columns per task. I will use the results from the papers though.

plonerma commented 3 years ago

I think this might integrate nicer then a screenshot

plonerma commented 3 years ago

Before we didn't include empirical results, which (in my opinion) is actually good, since we are focusing on the theory. But I think it would be nice to show at the end: the methods are different, but all produce reasonably good results...

=> That might also be a good justification of why we even cover all of them: there is no clear winner.

plonerma commented 3 years ago

Empricial results added in 052fdcf35f7290b2207e268f7b8ca9f82b543827