Evaluating models without test data (Practical AI #194)
Changelog Master Feed
English - September 20, 2022 19:20 - 44 minutes - 41.3 MB - ★★★★ - 28 ratingsTechnology Education How To changelog open source oss software development developer hacker Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
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.
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 – Twitter, GitHub, LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, Website
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!