{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Practical AI","title":"Evaluating models without test data","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/0c672de3\"></iframe>","width":"100%","height":180,"duration":2693,"description":"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.\n\nFeaturing:\nCharles Martin – GitHub, LinkedIn, X\nChris Benson – Website, GitHub, LinkedIn, X\nDaniel Whitenack – Website, GitHub, X\nShow Notes:\nWeightWatcher\nTalk from the Silicon Valley ACM meetup\nA deep dive into the theory behind WeightWatcher (a talk from ENS)\nUpcoming Events: \nRegister for upcoming webinars here!","thumbnail_url":"https://img.transistorcdn.com/Ox7ZlyiQOhdDa4Qy1MnJH5WFoksAetrzb40Jo1pePFs/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8wMTZi/ZWJmNWIwNDdmYTcw/NGJjMTExZjNjZmYy/M2ZjNS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}