Evaluating models without test data

Practical AI

EpisodeSep 20, 202244m

Evaluating models without test data

Practical AI

EpisodeSep 20, 202244m

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.Featuring:Charles Martin – GitHub, LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:WeightWatcherTalk from the Silicon Valley ACM meetupA deep dive into the theory behind WeightWatcher (a talk from ENS)Upcoming Events: Register for upcoming webinars here!

Top comments

Making artificial intelligence practical, productive & accessible to everyone. Practical AI is a show in which technology professionals, business people, students, enthusiasts, and expert guests engage in lively discussions about Artificial Intelligence and related topics (Machine Learning, Deep Learning, Neural Networks, GANs, MLOps, AIOps, LLMs & more). The focus is on productive implementations and real-world scenarios that are accessible to everyone. If you want to keep up with the latest advances in AI, while keeping one foot in the real world, then this is the show for you!

practicalai.fm

Switch to the Fountain App

Open in Fountain