undefined

Charles Martin

AI and data science consultant with Calculation Consulting. Creator of WeightWatcher, an open-source diagnostic tool for analyzing neural networks.

Top 5 podcasts with Charles Martin

Ranked by the Snipd community
undefined
24 snips
Apr 1, 2024 • 1h 6min

What Is Finished? - S13E7

Pastor Joby, with guests Jonathan Vinke, Ryan Britt, and Charles Martin, delves into Jesus' final words on the cross 'Tetelestai'. They explore the meaning of 'It is finished' and its implications, emphasizing the importance of deepening one's relationship with God. The podcast aims to help listeners discover and strengthen their connection with Jesus Christ through insightful conversations.
undefined
20 snips
Mar 24, 2024 • 1h 4min

The Opposite of Death - S13E6

Pastor Joby Martin, Pastor Jonathan Vinke, Pastor Ryan Britt, and special guest Charles Martin discuss the significance of Jesus's final words on the cross, exploring the Old Testament scripture referenced. They delve into the connections between Jesus and creation, symbolism of Gethsemane, and the Trinity's intricate layers. The conversation also touches on the unity between Jesus and the Father, eternal judgments, and the transformative power of facing judgment from Jesus.
undefined
14 snips
Sep 20, 2022 • 45min

Evaluating models without test data

Charles Martin, an AI and data science consultant, created WeightWatcher, a unique tool for analyzing neural networks without needing test data. In this discussion, he dives into the challenges of evaluating machine learning models, especially in fields like retail and finance. He emphasizes the significance of human judgment and innovative methods for model assessment. Martin also highlights the integration of statistical methods from physics in AI, showcasing how they can enhance model training and optimization processes.
undefined
13 snips
Mar 31, 2025 • 52min

WeightWatcher: The AI Detective for LLMs (DeepSeek & OpenAI included) (Ep. 278)

This week, Charles Martin, an AI specialist and the inventor of WeightWatcher, dives into the fascinating realm of large language models. He discusses how WeightWatcher acts as a detective tool for analyzing neural networks without needing internal data. The conversation explores advancements in AI, the relationship between theoretical research and practical applications, and the intricacies of model fine-tuning, comparing it to baking a cake. Martin also highlights the future of AI tools and the importance of community feedback to enhance their effectiveness.
undefined
11 snips
Sep 20, 2022 • 45min

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. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Featuring:Charles Martin – GitHub, LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow 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!

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app