filmov
tv
Stanford CS25: V1 I Transformers United: DL Models that have revolutionized NLP, CV, RL
Показать описание
Since their introduction in 2017, transformers have revolutionized Natural Language Processing (NLP). Now, transformers are finding applications all over Deep Learning, be it computer vision (CV), reinforcement learning (RL), Generative Adversarial Networks (GANs), Speech or even Biology. Among other things, transformers have enabled the creation of powerful language models like GPT-3 and were instrumental in DeepMind's recent AlphaFold2, that tackles protein folding.
In this speaker series, we examine the details of how transformers work, and dive deep into the different kinds of transformers and how they're applied in different fields. We do this by inviting people at the forefront of transformers research across different domains for guest lectures.
0:00 Introduction
2:43 Overview of Transformers
6:03 Attention mechanisms
7:53 Self retention
11:38 Other necessary ingredients
13:32 Encoder Decoder Architecture
16:02 Advantages & Disadvantages
18:04 Applications of Transformers
In this speaker series, we examine the details of how transformers work, and dive deep into the different kinds of transformers and how they're applied in different fields. We do this by inviting people at the forefront of transformers research across different domains for guest lectures.
0:00 Introduction
2:43 Overview of Transformers
6:03 Attention mechanisms
7:53 Self retention
11:38 Other necessary ingredients
13:32 Encoder Decoder Architecture
16:02 Advantages & Disadvantages
18:04 Applications of Transformers
0:22:44
Stanford CS25: V1 I Transformers United: DL Models that have revolutionized NLP, CV, RL
0:59:34
Stanford CS25: V1 I Transformer Circuits, Induction Heads, In-Context Learning
1:05:44
Stanford CS25: V1 I Mixture of Experts (MoE) paradigm and the Switch Transformer
1:05:43
Stanford CS25: V1 I Self Attention and Non-parametric transformers (NPTs)
1:20:43
Stanford CS25: V1 I Decision Transformer: Reinforcement Learning via Sequence Modeling
1:08:37
Stanford CS25: V1 I Transformers in Vision: Tackling problems in Computer Vision
0:58:59
Stanford CS25: V1 I DeepMind's Perceiver and Perceiver IO: new data family architecture
1:01:28
clear voice CS25 Transformers United 2023 Introduction to Transformers w Andrej Karpathy
1:22:13
Stanford CS25: V2 I Neuroscience-Inspired Artificial Intelligence
1:01:37
Stanford CS25: V4 I Behind the Scenes of LLM Pre-training: StarCoder Use Case
0:55:27
Mechanistic Interpretability - Stella Biderman | Stanford MLSys #70
0:15:56
Transformers - Part 1 - Self-attention: an introduction
0:10:57
5 Free LLM Courses RoadMap in 2023
0:58:23
Sparse Expert Models (Switch Transformers, GLAM, and more... w/ the Authors)
0:23:41
25. Transformers
0:28:52
Transformers for Structural Extraction
0:00:21
The Surprising World of Mechanistic Interpretability Unlocking AI Secrets
0:00:45
Cross Attention vs Self Attention
1:00:58
Transformer Circuits Part 1
0:00:51
Contrastive Decision Transformers
2:50:14
A Walkthrough of A Mathematical Framework for Transformer Circuits
0:01:54
What is Transformer? Electrical transformers | Introduction #engineering #electricalengineering
0:00:59
Neel Nanda on mechanistic interpretability #artificialintelligence #gpt
0:04:47
Minae Kwon's talk on 'Reward Design with Language Models'
Комментарии