Skip to content

Instantly share code, notes, and snippets.

@eamartin

eamartin/notebook.ipynb

Last active April 22, 2025 08:11
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save eamartin/d7f1f71e5ce54112fe05e2f2f17ebedf to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save eamartin/d7f1f71e5ce54112fe05e2f2f17ebedf to your computer and use it in GitHub Desktop.
Download ZIP
Understanding & Visualizing Self-Normalizing Neural Networks
Display the source blob
Display the rendered blob
Raw
notebook.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@wtesler

wtesler commented Jul 17, 2017

Copy link
Copy Markdown

Awesome

@gklambauer

gklambauer commented Jul 17, 2017

Copy link
Copy Markdown

Nice work!

@smoussa

smoussa commented Jul 19, 2017

Copy link
Copy Markdown

Brilliant :) Very clear.

@gngdb

gngdb commented Jul 28, 2017

Copy link
Copy Markdown

Was wondering if this also worked for convolutional networks, so added a section to this notebook with a conv2d experiment. It's here: https://gist.github.com/gngdb/a122ae86c0b897cffebdb9481e321c9d

@mschulkind

mschulkind commented Aug 5, 2017

Copy link
Copy Markdown

Recall the special property of the activation function is to map ... Var[h] = 0

Don't you mean Var[h] = 1?

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