09L – Differentiable associative memories, attention, and transformers
Course website: http://bit.ly/DLSP21-web
Playlist: http://bit.ly/DLSP21-YouTube
Speaker: Yann LeCun
Chapters
00:00:00 – Motivation for reasoning & planning
00:09:11 – Inference through energy minimization
00:18:08 – Disclaimer
00:19:02 – Planning through energy minimization
00:32:59 – Q&A Optimal control diagram
00:39:23 – Differentiable associative memory and attention
01:01:03 – Transformers
01:08:14 – Q&A Other differentiable attention architectures
01:10:32 – Transformer architecture
01:27:54 – Transformer applications: 1. Multilingual transformer Architecture XML-R
01:30:16 – 2. Supervised symbol manipulation
01:32:14 – 3. NL understanding & generation
01:36:51 – 4. DETR
01:46:47 – Planing through optimal control
01:55:37 – Conclusion
Видео 09L – Differentiable associative memories, attention, and transformers канала Alfredo Canziani
Playlist: http://bit.ly/DLSP21-YouTube
Speaker: Yann LeCun
Chapters
00:00:00 – Motivation for reasoning & planning
00:09:11 – Inference through energy minimization
00:18:08 – Disclaimer
00:19:02 – Planning through energy minimization
00:32:59 – Q&A Optimal control diagram
00:39:23 – Differentiable associative memory and attention
01:01:03 – Transformers
01:08:14 – Q&A Other differentiable attention architectures
01:10:32 – Transformer architecture
01:27:54 – Transformer applications: 1. Multilingual transformer Architecture XML-R
01:30:16 – 2. Supervised symbol manipulation
01:32:14 – 3. NL understanding & generation
01:36:51 – 4. DETR
01:46:47 – Planing through optimal control
01:55:37 – Conclusion
Видео 09L – Differentiable associative memories, attention, and transformers канала Alfredo Canziani
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
14L – Lagrangian backpropagation, final project winners, and Q&A session
12 – Planning and control
Practical 4.1 – RNN forward and backward
Week 15 – Practicum part B: Training latent variable energy based models (EBMs)
Chapter 2, video 4–6
Behind the scenes
TeraDeep Image Parser
02 – Supervised learning / Classification
Person detector
Practical 3.2 – CNN models
Week 9 – Practicum: (Energy-based) Generative adversarial networks![[LIVE] Free energy gentle introduction](https://i.ytimg.com/vi/y6WNrHskm2E/default.jpg)
[LIVE] Free energy gentle introduction
Purdue theme
08 – From LV-EBM to target prop to (vanilla, denoising, contractive, variational) autoencoder
06L – Latent variable EBMs for structured prediction
Why not?
Matrix multiplication, signals, and convolutions
Practical 3.3 – CNN training
Goodbye to DL20,21,22,23 apartment
Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic
05 – Multi-class perceptron, binary and multi-class logistic regression