Evaluating models without test data (Practical AI #194)
WeightWatcher, created by Charles Martin, is an open source diagnostic tool for analyzing Neural Networks without training or even test data! Charles joins us in this episode to discuss the tool and how it fills certain gaps in current model evaluation workflows. Along the way, we discuss statistical methods from physics and a variety of practical ways to modify your training runs.
Changelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!
Featuring:
- Charles Martin – GitHub, LinkedIn, X
- Chris Benson – Website, GitHub, LinkedIn, Bluesky, X
- Daniel Whitenack – Website, GitHub, X
Show Notes:
- WeightWatcher
- Talk from the Silicon Valley ACM meetup
- A deep dive into the theory behind WeightWatcher (a talk from ENS)
Something missing or broken? PRs welcome!
You May Also Like
Computer Club
Computer Club - Freddy & Smollie

TyfloPodcast
TyfloPodcast

Cloud Posse DevOps "Office Hours" Podcast
Erik Osterman

AI News Daily
brief.news

Theo - t3․gg
Theo - t3․gg

Jack Hopkins
Jack Hopkins

Macworld Podcast
Foundry

The AI Daily Brief: Artificial Intelligence News and Analysis
Nathaniel Whittemore

Hacker Valley Studio
Hacker Valley Media

The Good Tech Companies
HackerNoon
Community discussion