New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Better documentation #70

Open

gdalle opened this issue Jun 28, 2023 · 1 comment · May be fixed by #102

Labels

Milestone

Collaborator

gdalle commented Jun 28, 2023

We urgently need a better documentation with

a better intro to the theory
examples for all types of loss functions
examples for using kwargs to pass instances (Clarify & demonstrate use of kwargs #56)
a guide for choosing your layer à la scikit-learn

gdalle added the documentation label

gdalle added this to the v0.5 milestone

Collaborator Author

gdalle commented Jun 29, 2023

I also wanna write an explanation of the design of the library:

there are layers and losses, all callable
some layers are probabilistic, others not, but all are differentiable
most losses must be built with a layer
if you have your own differentiable loss you can compose it with a layer
if you have your own non-differentiable loss you can pushforward it with a probabilistic layer

BatyLeo modified the milestones: v0.6, v0.7

BatyLeo linked a pull request

that will close this issue

Documentation revamp #102

Draft

11 tasks

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment