Skip to content

Archive

Home Browse Courses Talks Study Paths

Directory

Institutions Speakers

Library

Playlists

Speakers/William Fedus

/

/

Speakers/William Fedus

Faculty & Researcher Profile

William Fedus

Professor at Stanford University

William Fedus is a professor at Stanford University, specializing in machine learning and the development of transformer models and mixture of experts.

1course·9total lectures·10hrecorded

Stanford University AI & Machine LearningCo-taught withAshish Vaswani Lucas Beyer Trenton Bricken Drew Jaegle

Books & course texts for William Fedus

Amazon Associate

Build a Large Language Model (From Scratch)

Build a Large Language Model (From Scratch)

Course TextbookManning Publications · 1st Edition (2024)

Build a Large Language Model (From Scratch)

By Sebastian Raschka

Step-by-step architectural guide to implementing tokenization, multi-head self-attention, pretraining, and alignment from first principles.

Assigned syllabus textbook in this scholar's course·ISBN 978-1633437166

Courses by William Fedus

All courses →

Complete university lecture series taught by William Fedus.

Stanford CS25: Transformers United

Stanford University · CS259 lectures · 10h

AI & ML·graduate

Transformers United

Ashish Vaswani&Lucas Beyer

Research seminar examining self-attention architectures across language modeling, multimodal reasoning, robotics, biology, and scaling laws with leading industry and academic pioneers.

Start lecture 1

Study paths featuring William Fedus

1

All study paths →

Mechanistic Interpretability, Alignment & World Models

6 steps · 5h5 universities

EditorialAI & ML·research

Mechanistic Interpretability, Alignment & World Models

From neural circuits to scalable oversight: understanding and controlling advanced AI systems.

Association for Computing Machinery (ACM) · Stanford University · Harvard University +2

6 curated lecturesOpen path →

All lectures by William Fedus

9

Search or browse every recorded session across courses and talks.

Showing 9 of 9 lectures

jknavigate↵watchcchaptersssavexwatched

Save

Transformer Circuits, Induction Heads, In-Context Learning

Transformer Circuits, Induction Heads, In-Context Learning

CS25 · Transformers United · Lec 7·Mechanistic Interpretability, Alignment & World Models · Ashish Vaswani, Lucas Beyer & William Fedus · Stanford University

Ashish Vaswani&Lucas Beyer

Stanford University

—

59:34

Decision Transformer: Reinforcement Learning via Sequence Modeling

Decision Transformer: Reinforcement Learning via Sequence Modeling

CS25 · Transformers United · Lec 3·Reinforcement Learning · Ashish Vaswani, Lucas Beyer & William Fedus · Stanford University

Ashish Vaswani&Lucas Beyer

Stanford University

—

1:20:42

Transformers United: DL Models that have revolutionized NLP, CV, RL

Transformers United: DL Models that have revolutionized NLP, CV, RL

CS25 · Transformers United · Lec 1·Deep Learning · Ashish Vaswani, Lucas Beyer & William Fedus · Stanford University

Ashish Vaswani&Lucas Beyer

Stanford University

22:43

Mixture of Experts (MoE) paradigm and the Switch Transformer

Mixture of Experts (MoE) paradigm and the Switch Transformer

CS25 · Transformers United · Lec 4·Deep Learning · Ashish Vaswani, Lucas Beyer & William Fedus · Stanford University

Ashish Vaswani&Lucas Beyer

Stanford University

—

1:05:44

Self Attention and Non-parametric transformers (NPTs)

Self Attention and Non-parametric transformers (NPTs)

CS25 · Transformers United · Lec 6·Deep Learning · Ashish Vaswani, Lucas Beyer & William Fedus · Stanford University

Ashish Vaswani&Lucas Beyer

Stanford University

—

1:05:43

How I Learned to Stop Worrying and Love the Transformer

How I Learned to Stop Worrying and Love the Transformer

CS25 · Transformers United · Lec 9·Deep Learning · Ashish Vaswani · Stanford University

Stanford University

—

1:20:38

Neuroscience-Inspired Artificial Intelligence

Neuroscience-Inspired Artificial Intelligence

CS25 · Transformers United · Lec 8·Neuroscience & Cognition · Trenton Bricken · Stanford University

Trenton Bricken

Stanford University

—

1:22:14

DeepMind's Perceiver and Perceiver IO: New data family architecture

DeepMind's Perceiver and Perceiver IO: New data family architecture

CS25 · Transformers United · Lec 5·Deep Learning · Drew Jaegle · Stanford University

Stanford University

—

58:58

Transformers in Vision: Tackling problems in Computer Vision

Transformers in Vision: Tackling problems in Computer Vision

CS25 · Transformers United · Lec 2·Language Models & NLP · Lucas Beyer · Stanford University

Stanford University

—

1:08:36

Showing 9 of 9 lectures·9.7h shown