April 18, 2023, 7:32 a.m. | Aaron Master

Towards Data Science - Medium towardsdatascience.com

The case for GOOD diagrams

Image by the authors, adapted from https://tikz.net/neural_networks/ (CC BY-SA 4.0)

By Aaron Master and Doron Bergman

If you’re one of the millions of people who has tried to learn neural networks, odds are you’ve seen something like the above image.

There’s just one problem with this diagram: it’s nonsense.

By which we mean confusing, incomplete, and probably wrong. The diagram, inspired by one in a famous online Deep Learning course, excludes all of the bias …

deep learning education humor networks neural networks visualization

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Senior Software Engineer, Generative AI (C++)

@ SoundHound Inc. | Toronto, Canada