Naftali Tishby - The Information Bottleneck View of Deep Learning: Why do we need it?
Speaker: Naftali Tishby Title: The Information Bottleneck View of Deep Learning: Why do we need it? Presented at the 2019 Conference on the Mathematical Theory of Deep Learning (DeepMath 2019)
▶︎
Boris Hanin - NTK in ReLU Nets with Finite Depth and Width
▶︎
The Information Bottleneck Theory of Deep Neural Networks...
▶︎
001. Information Theory of Deep Learning - Naftali Tishby
▶︎
Concept Bottleneck Models (Paper Explained)
▶︎
Terence Tao: Nobody Understands Why AI Actually Works
▶︎
Optimal Transport and Information Geometry for Machine Learning and Data Science
▶︎
The Uncomfortable Truth About AI “Reasoning” | World Science Festival
▶︎
Sanjeev Arora: Why do deep nets generalize, that is, predict well on unseen data
▶︎
Stanford Seminar - Information Theory of Deep Learning, Naftali Tishby
▶︎
Why LeCun Thinks Deep Learning Isn't Enough — Yann LeCun
▶︎
Web Scraping Using Python For Beginners and File Handling in Python | Python Web Scraping
▶︎
Stephanie Palmer: "Information bottleneck approaches to quantifying prediction in the brain"
▶︎
Transformers, the tech behind LLMs | Deep Learning Chapter 5
▶︎
Michael Elad - Sparse Modelling of Data and its Relation to Deep Learning
▶︎
Bayesian Deep Learning and Probabilistic Model Construction - ICML 2020 Tutorial
▶︎
AlphaFold - The Most Useful Thing AI Has Ever Done
▶︎
Computer Science | D3S4 14/18 AI & Autonomous Systems – Part II - Similarities... - Naftali Tishby
▶︎
Запись трансляции "Information Theory of Deep Learning" (проф.Naftali Tishby)
▶︎
Gradient descent, how neural networks learn | Deep Learning Chapter 2
▶︎