[122] על הקשר בין דחיסה ללמידה עם פרופ. רביד זיו

What this episode covers

רביד זיו, לשעבר מהמעבדה של יאן לקון, היום פרופסור בNYU וחוקר פורה בדיפ לרנינג ידבר איתנו על דחיסה ולמידה.בעוד דחיסה מזכיר לחלקנו זיפ, או jpeg - רביד ירחיב על איך רשתות דוחסות מידע בצורה יעילה.נדבר על שיטות כגון next token prediction שמסתבר שמאלצות מודלים ללמוד דחיסה יעילה יותר מאשר masking כמו בBERT.נדבר על חשיבות האוגמנטציה בתהליך האימון - או יותר נכון, חוסר החשיבות כפי שנראה.ונעמיק על הקשר שבין דחיסת מודלים, דחיסת אינפורמציה והמשימות אליהן רוצים לעשות אופטימיזציה

Share this episode

Similar Episodes

The Climb You Have to Make to Conquer AI

Jun 21, 2026 ·17m

The Geometry of Human Sovereignty

Jun 19, 2026 ·20m

The AI Brain for Real Intelligence with Bruno Maisonnier

Jun 11, 2026 ·58m

Reclaiming Accountability in the Machine Age

Jun 6, 2026 ·21m

The future of AI: Proactive agents, wearables and brain interfaces with Terry Schussler

Jun 4, 2026 ·54m

The Language of Creative Impact

Jun 4, 2026 ·21m

Similar Podcasts

Spatial Web AI Podcast Denise Holt Active Inference AI & the Spatial Web The Future of AI is shared, distributed, and multi-scale.AI that is knowable, explainable, and capable of human governance.Based on the same mechanics as biological intelligence, it operates in a naturally efficient way, with no big data requirement.This is Active Inference AI & the Spatial Web. Trustworthy AI : De-risk business adoption of AI Pamela Gupta Description: Creating AI Trust is a very complex and hard problem. It is not clear what it is and how it can be operationalized. We will demystify what is Trustworthy AI, efficient adoption and leveraging it for reducing risks in AI programs.McKinsey reports indicates companies seeing the biggest bottom-line returns from AI—those that attribute at least 20 percent of EBIT or profitability to their use of AI—are more likely than others to follow Trustworthy AI best practices, including explainability. Further, organizations that establish digital trust among consumers through responsible practices such as making AI explainable are more likely to see their annual revenue and profitability grow at rates of 10 percent or more. Evidence → Cognition → Discernment™️ - Your Pathway to AI Leadership Greg Twemlow XperientialAI — Pathway to AI Leadership explores how people can collaborate with AI without outsourcing judgment. The spine is a three-step method: Evidence → Cognition → Discernment — a bridge from what’s scattered to what’s chosen. Through essays, reflections, and practical examples, I show how the Context & Critique Rule™ keeps thinking visible, decisions explainable, and responsibility human. Known Unknowns Known Unknowns Known Unknowns podcast explores unexplainable mysteries. We discuss the things that lie on the fringes of reality. Things that we know that are unknown.Ghosts, Folklore, Conspiracies, and everything else that lies outside the realm of the explainable...Because it's weird out there.

Frequently Asked Questions

How long is this episode of ExplAInable?

This episode is 56 minutes long.

When was this ExplAInable episode published?

This episode was published on June 15, 2025.

What is this episode about?

רביד זיו, לשעבר מהמעבדה של יאן לקון, היום פרופסור בNYU וחוקר פורה בדיפ לרנינג ידבר איתנו על דחיסה ולמידה.בעוד דחיסה מזכיר לחלקנו זיפ, או jpeg - רביד ירחיב על איך רשתות דוחסות מידע בצורה יעילה.נדבר על שיטות כגון next token prediction שמסתבר שמאלצות...

Can I download this ExplAInable episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.