First impression of Fable: a lot more concise out of the box. Example of asking it to prototype optimizer updates https://github.com/yaroslavvb/learning-rotations
First impression of Fable: a lot more concise out of the box. Example of asking it to prototype optimizer updates https://github.com/yaroslavvb/learning-rotations
Method 3 is a good example of a non-"gradient descent"-based learning, a multiplicative update
First impression of Fable: a lot more concise out of the box. Example of asking it to prototype optimizer updates https://github.com/yaroslavvb/learning-rotations
The design sense of Fable is really nice, colors come out consistently on first try https://yaroslavvb.github.io/learning-rotations/
First impression of Fable: a lot more concise out of the box. Example of asking it to prototype optimizer updates https://github.com/yaroslavvb/learning-rotations
First impression of Fable: a lot more concise out of the box. Example of asking it to prototype optimizer updates https://github.com/yaroslavvb/learning-rotations