Grokking, Generalization Collapse, and the Dynamics of Training Deep Neural Networks with Charles Martin - #734

Grokking, Generalization Collapse, and the Dynamics of Training Deep Neural Networks with Charles Martin - #734

Today, we're joined by Charles Martin, founder of Calculation Consulting, to discuss Weight Watcher, an open-source tool for analyzing and improving Deep Neural Networks (DNNs) based on principles from theoretical physics. We explore the foundations of the Heavy-Tailed Self-Regularization (HTSR) theory that underpins it, which combines random matrix theory and renormalization group ideas to uncover deep insights about model training dynamics. Charles walks us through WeightWatcher’s ability to detect three distinct learning phases—underfitting, grokking, and generalization collapse—and how its signature “layer quality” metric reveals whether individual layers are underfit, overfit, or optimally tuned. Additionally, we dig into the complexities involved in fine-tuning models, the surprising correlation between model optimality and hallucination, the often-underestimated challenges of search relevance, and their implications for RAG. Finally, Charles shares his insights into real-world applications of generative AI and his lessons learned from working in the field. The complete show notes for this episode can be found at https://twimlai.com/go/734.

Jaksot(783)

Mamba, Mamba-2 and Post-Transformer Architectures for Generative AI with Albert Gu - #693

Mamba, Mamba-2 and Post-Transformer Architectures for Generative AI with Albert Gu - #693

Today, we're joined by Albert Gu, assistant professor at Carnegie Mellon University, to discuss his research on post-transformer architectures for multi-modal foundation models, with a focus on state-...

17 Heinä 202457min

Decoding Animal Behavior to Train Robots with EgoPet with Amir Bar - #692

Decoding Animal Behavior to Train Robots with EgoPet with Amir Bar - #692

Today, we're joined by Amir Bar, a PhD candidate at Tel Aviv University and UC Berkeley to discuss his research on visual-based learning, including his recent paper, “EgoPet: Egomotion and Interaction...

9 Heinä 202443min

How Microsoft Scales Testing and Safety for Generative AI with Sarah Bird - #691

How Microsoft Scales Testing and Safety for Generative AI with Sarah Bird - #691

Today, we're joined by Sarah Bird, chief product officer of responsible AI at Microsoft. We discuss the testing and evaluation techniques Microsoft applies to ensure safe deployment and use of generat...

1 Heinä 202457min

Long Context Language Models and their Biological Applications with Eric Nguyen - #690

Long Context Language Models and their Biological Applications with Eric Nguyen - #690

Today, we're joined by Eric Nguyen, PhD student at Stanford University. In our conversation, we explore his research on long context foundation models and their application to biology particularly Hye...

25 Kesä 202445min

Accelerating Sustainability with AI with Andres Ravinet - #689

Accelerating Sustainability with AI with Andres Ravinet - #689

Today, we're joined by Andres Ravinet, sustainability global black belt at Microsoft, to discuss the role of AI in sustainability. We explore real-world use cases where AI-driven solutions are leverag...

18 Kesä 202447min

Gen AI at the Edge: Qualcomm AI Research at CVPR 2024 with Fatih Porikli - #688

Gen AI at the Edge: Qualcomm AI Research at CVPR 2024 with Fatih Porikli - #688

Today we’re joined by Fatih Porikli, senior director of technology at Qualcomm AI Research. In our conversation, we covered several of the Qualcomm team’s 16 accepted main track and workshop papers at...

10 Kesä 20241h 10min

Energy Star Ratings for AI Models with Sasha Luccioni - #687

Energy Star Ratings for AI Models with Sasha Luccioni - #687

Today, we're joined by Sasha Luccioni, AI and Climate lead at Hugging Face, to discuss the environmental impact of AI models. We dig into her recent research into the relative energy consumption of ge...

3 Kesä 202448min

Language Understanding and LLMs with Christopher Manning - #686

Language Understanding and LLMs with Christopher Manning - #686

Today, we're joined by Christopher Manning, the Thomas M. Siebel professor in Machine Learning at Stanford University and a recent recipient of the 2024 IEEE John von Neumann medal. In our conversatio...

27 Touko 202456min

Suosittua kategoriassa Politiikka ja uutiset

uutiscast
aikalisa
politiikan-puskaradio
ootsa-kuullut-tasta-2
rss-ootsa-kuullut-tasta
tervo-halme
rss-podme-livebox
rss-vaalirankkurit-podcast
rss-pinnalla
aihe
otetaan-yhdet
the-ulkopolitist
rss-asiastudio
rss-ulkopoditiikkaa
rss-raha-talous-ja-politiikka
rss-girls-finish-f1rst
viisupodi
et-sa-noin-voi-sanoo-esittaa
rss-tasta-on-kyse-ivan-puopolo-verkkouutiset
rss-vain-talouselamaa