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

Improve MNIST Tutorial based on User feedback #1

Open

cpehle opened this issue Jul 10, 2020 · 0 comments

Member

cpehle commented Jul 10, 2020 •

edited

Loading

There are a couple of confusing points in the current version of the MNIST tutorial

Surrogate gradients are not explained but parameters (method = "super", alpha=100) refer to them
There is insufficient explanation of the time integration aspect, which is the major difference to ANNs (c.f. integration loop)
MNIST normalisation isn't explained
We should visualise and elaborate more on the network architectures, as is the feature computations are rather opaque and non-obvious

Jegp mentioned this issue

Improved MNIST notebook #22

Closed

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