Lecture 2.4: Automatic Differentiation (DLVU)
In the final video of this lecture, we look at how to make the computer maintain a computation graph for us, so that all we have to do is define operations and define the forward pass.
lecturer: Peter Bloem
course site: https://dlvu.github.io
Видео Lecture 2.4: Automatic Differentiation (DLVU) канала DLVU
lecturer: Peter Bloem
course site: https://dlvu.github.io
Видео Lecture 2.4: Automatic Differentiation (DLVU) канала DLVU
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![[archived] Lecture 1.2: A quick intro to AI](https://i.ytimg.com/vi/i7-nhWSFsZ8/default.jpg)
[archived] Lecture 1.2: A quick intro to AI
Lecture 4.4 The bag of tricks
Lecture 4.2 Why does deep Learning work? (DLVU)
Lecture 11.3: World Models
Lecture 6.3: variational autoencoders
Lecture 1.1: Neural networks![[OLD] Lecture 2.4: Automatic Differentiation (DLVU)](https://i.ytimg.com/vi/UpLtbV4L6PI/default.jpg)
[OLD] Lecture 2.4: Automatic Differentiation (DLVU)
Lecture 7.2 Implicit models: GANs![[OLD] Lecture 2.2: Backpropagation, scalar perspective (DLVU)](https://i.ytimg.com/vi/7mTcWrnexkk/default.jpg)
[OLD] Lecture 2.2: Backpropagation, scalar perspective (DLVU)
Lecture 5.2 Recurrent Neural Networks
Lecture 8.1b: Introduction - Embeddings
Lecture 1.2: Regression, classification and loss functions
Lecture 2.1: A Review of Neural Networks (DLVU)
Lecture 8.2: Graph and node embedding
Lecture 6.2: Latent variable model
Lecture 9.3: Gradient Estimation
Lecture 8.4: Application - query embedding
Lecture 4.1 General Deep Learning practice
Lecture 10.2: ARM & Flows
Lecture 10.1: ARM & Flows
Lecture 12.4 Scaling up (Mixed precision, Data-parallelism, FSDP)