Completed
Adityanarayanan Radhakrishnan - How do neural networks learn features from data? - IPAM at UCLA
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Theory and Practice of Deep Learning 2024
Automatically move to the next video in the Classroom when playback concludes
- 1 Adityanarayanan Radhakrishnan - How do neural networks learn features from data? - IPAM at UCLA
- 2 Leena Vankadara - Scaling Insights from Infinite-Width Theory for Next Gen Architecture & Learning
- 3 Sam Smith - How to train an LLM - IPAM at UCLA
- 4 Elvis Dohmatob - The Mathematics of Scaling Laws and Model Collapse in AI - IPAM at UCLA
- 5 Dmitry Krotov - Generative AI models through the lens of Dense Associative Memory - IPAM at UCLA
- 6 Blake Bordelon - Infinite limits and scaling laws of neural networks - IPAM at UCLA
- 7 Gintare Karolina Dziugaite - The dynamics of memorization and generalization in deep learning
- 8 Misha Belkin - Emergence and grokking in "simple" architectures - IPAM at UCLA
- 9 Oliver Eberle - Interpretability for Deep Learning: Theory, Applications and Scientific Insights
- 10 Boris Hanin - Neural Network Scaling Limits - IPAM at UCLA
- 11 Paul Riechers - geometric representation of far future in deep neural networks trained on next-token
- 12 Fanny Yang - Surprising phenomena of max-lp-margin classifiers in high dimensions - IPAM at UCLA
- 13 Cengiz Pehlevan - 2 stories in mechanistic interpretation of natural & artificial neural computation
- 14 Mauro Maggioni - On exploiting compositional structure: one bit of theory and one application
- 15 Dan Roy - Size of Teachers as Measure of Data Complexity: PAC-Bayes Excess Risk Bounds & Scaling Law
- 16 Vidya Muthukumar - Comparison and transfer between tasks in overparameterized learning
- 17 Mayank Mehta - Dynamics of brain's deep network - IPAM at UCLA
- 18 Nikos Tsilivis - The Price of Implicit Bias in Robust ML - IPAM at UCLA
- 19 Wu Lin - A framework for designing (non-diagonal) adaptive training methods - IPAM at UCLA
- 20 Shaowei Lin - Singular Learning, Relative Information and the Dual Numbers - IPAM at UCLA
- 21 Patrick Shafto - Common Ground in Cooperative Communication - IPAM at UCLA
