While Model Trains

Read data blog posts.
Carefully handpicked.
Presented 3 at a time.

Finding bad flamingo drawings with recurrent neural networks

Colin Morris

Using Sketch-RNN as a probability estimator to identify the worst sketches of flamingos in 'Quick, Draw!'.

Read it!

How much data should you allocate to training and validation?

Francesco Pochetti

To avoid responding with "that's what Andrew NG said" when asked about the reason behind choosing an 80% training and 20% validation split, consider this explanation.

Read it!

An Introduction to different Types of Convolutions in Deep Learning

Paul-Louis Pröve

Dilated, transposed, and separable convolutions explained with informative animations.

Read it!