Ranlot

vor 7 Jahrendiscuss

For those interested in a clear explanation of the backward pass (especially for convolution layers), here's a good resource:

https://arxiv.org/abs/1811.11987

https://github.com/Ranlot/backpropagation-CNNs

Ranlot

vor 8 Jahrendiscuss

Looks like another cool app: Click somewhere on the coastline and it'll take you to what's directly on the other side of the sea. Results may be surprising:

https://ranlot.shinyapps.io/coastlinetrip/

Ranlot

vor 9 Jahrendiscuss

Reminds me of this app. Showing what lies directly across the ocean: https://ranlot.shinyapps.io/coastlinetrip/

Ranlot

vor 9 Jahrendiscuss

Imagine you're standing on your favorite beach and stare straight out into the sea.

What place on Earth would you really end up in if you followed this path?

And which countries would you cross until you come back home?

Ranlot

vor 9 Jahrendiscuss

This reminds me of this discussion about AB testing, power statistics & significance: https://p-value-convergence.herokuapp.com/

Ranlot

vor 9 Jahrendiscuss

A simple discussion to find out more about the "statistical power" mentioned in the article: https://p-value-convergence.herokuapp.com/

Submissions

Public key encryption for pedestrians: RSA and OAEP padding with a real SSH key

Public key encryption for pedestrians: RSA and OAEP padding with a real SSH key

Fit any data with 1 parameter 300 stars on GitHub

Real numbers, data science and chaos: Fit any dataset with a single parameter

Deep learning for pedestrians: backpropagation in CNNs

Deep learning for pedestrians: backpropagation in CNNs

Manifold hypothesis, neural nets & optimal packing: look into the hidden layers

What's really on the other side of the sea? a small geographical app shows you

Reproducibility crisis: some notes about p-values that may be of interest

Statistical significance of AB tests? Online calculator and short discussion

comments