While Model Trains

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

Why is machine learning 'hard'?

S. Zayd Enam

"The difficulty is that machine learning is a fundamentally hard debugging problem. Debugging for machine learning happens in two cases: 1) your algorithm doesn't work or 2) your algorithm doesn't work well enough."

Read it!

It's ML, not magic: simple questions you should ask to help reduce AI hype

Stephen Merity

A series of questions to maintain control over the hype surrounding AI. Always more relevant.

Read it!

How to Visualize Filters and Feature Maps in Convolutional Neural Networks

Jason Brownlee

A tutorial on how to gain insights into a CNN by visualizing filters and feature maps.

Read it!