Machine Learning Street Talk (MLST)25 Feb 2021

#044 - Data-efficient Image Transformers (Hugo Touvron)

Today we are going to talk about the *Data-efficient image Transformers paper or (DeiT) which Hugo is the primary author of. One of the recipes of success for vision models since the DL revolution began has been the availability of large training sets. CNNs have been optimized for almost a decade now, including through extensive architecture search which is prone to overfitting. Motivated by the success of transformers-based models

in Natural Language Processing there has been increasing attention in applying these approaches to vision models. Hugo and his collaborators used a different training strategy and a new distillation token to get a massive increase in sample efficiency with image transformers.

00:00:00 Introduction

00:06:33 Data augmentation is all you need

00:09:53 Now the image patches are the convolutions though?

00:12:16 Where are those inductive biases hiding?

00:15:46 Distillation token

00:21:01 Why different resolutions on training

00:24:14 How data efficient can we get?

00:26:47 Out of domain generalisation

00:28:22 Why are transformers data efficient at all? Learning invariances

00:32:04 Is data augmentation cheating?

00:33:25 Distillation strategies - matching the intermediatae teacher representation as well as output

00:35:49 Do ML models learn the same thing for a problem?

00:39:01 How is it like at Facebook AI?

00:41:17 How long is the PhD programme?

00:42:03 Other interests outside of transformers?

00:43:18 Transformers for Vision and Language

00:47:40 Could we improve transformers models? (Hybrid models)

00:49:03 Biggest challenges in AI?

00:50:52 How far can we go with data driven approach?

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(252)

When AI Decides You're a Threat — Brad Carson

Brad Carson was the Army's General Counsel, served two terms in Congress and was Acting Under Secretary of Defense for Personnel and Readiness. He now heads Americans for Responsible Innovation, the A...

31 Maj 1h 20min

Intelligence is collective, not artificial — Prof. Michael I. Jordan (UC Berkeley / Inria)

Michael I. Jordan, described by Science magazine as the most influential computer scientist alive, has never thought of himself as an AI researcher. In this conversation he explains why that distincti...

21 Maj 1h 17min

The AI Models Smart Enough to Know They're Cheating — Beth Barnes & David Rein [METR]

Beth Barnes and David Rein on the one graph that ate the AI timelines discourse, and why the two people who built it are the most careful about how you read it.**SPONSOR**Prolific - Quality data. From...

4 Maj 1h 53min

When AI Discovers The Next Transformer - Robert Lange (Sakana)

Robert Lange, founding researcher at Sakana AI, joins Tim to discuss *Shinka Evolve* — a framework that combines LLMs with evolutionary algorithms to do open-ended program search. The core claim: syst...

13 Mars 1h 18min

"Vibe Coding is a Slot Machine" - Jeremy Howard

Dive into the realities of AI-assisted coding, the origins of modern fine-tuning, and the cognitive science behind machine learning with fast.ai founder Jeremy Howard. In this episode, we unpack why A...

3 Mars 1h 26min

Evolution "Doesn't Need" Mutation - Blaise Agüera y Arcas

What if life itself is just a really sophisticated computer program that wrote itself into existence?Blaise Agüera y Arcas presenting at ALife 2025 — the most technically detailed public walkthrough o...

16 Feb 55min

VAEs Are Energy-Based Models? [Dr. Jeff Beck]

What makes something truly *intelligent?* Is a rock an agent? Could a perfect simulation of your brain actually *be* you? In this fascinating conversation, Dr. Jeff Beck takes us on a journey through ...

25 Jan 46min

Abstraction & Idealization: AI's Plato Problem [Mazviita Chirimuuta]

Professor Mazviita Chirimuuta joins us for a fascinating deep dive into the philosophy of neuroscience and what it really means to understand the mind.*What can neuroscience actually tell us about how...

23 Jan 53min