Programming for AI (AI504, Fall 2020), Practice 14: Neural Ordinary Differential Equations

preview_player
Показать описание
Neural Ordinary Differential Equations
- Implement ODE solvers
-- Euler's method
-- Runge-Kutta
- Implement Neural ODE
- Train with spirals
- Compare with adaptive step size solver
- compare with adjoint sensitivity method

  1. Edward Choi
Рекомендации по теме
Programming for AI 0:53:55

Programming for AI (AI504, Fall 2022), Class 1: Introduction

Programming for AI 1:43:04

Programming for AI (AI504, Fall 2020), Class 2: Basic Machine Learning

Programming for AI 1:36:17

Programming for AI (AI504, Fall 2022), Class 11: BERT & GPT

Programming for AI 0:59:37

Programming for AI (AI504, Fall 2023), Class 1: Introduction

Programming for AI 1:34:15

Programming for AI (AI504, Fall 2022), Class 2: Basic Machine Learning

Programming for AI 1:48:22

Programming for AI (AI504, Fall 2020), Class 7: Convolutional Neural Network

Programming for AI 1:34:34

Programming for AI (AI504, Fall 2020), Practice 10: Image to Text

Programming for AI 1:22:40

Programming for AI (AI504, Fall 2022), Practice 7: CNN & Project 1

Programming for AI 1:50:41

Programming for AI (AI504, Fall 2023), Class 2: Basic Machine Learning

Programming for AI 1:27:59

Programming for AI (AI504, Fall 2020), Class 10: Image to Text

Programming for AI 2:02:38

Programming for AI (AI504, Fall 2020), Practice 2: Basic Machine Learning

Programming for AI 1:47:48

Programming for AI (AI504, Fall 2020), Practice 1: Numpy

Programming for AI 1:42:54

Programming for AI (AI504, Fall 2020), Class 12: BERT & GPT

Programming for AI 2:08:23

Programming for AI (AI504, Fall 2020), Practice 7: Convolutional Neural Network

Programming for AI 1:36:16

Programming for AI (AI504, Fall 2022), Class 7: Convolutional Neural Network

Programming for AI 1:27:43

Programming for AI (AI504, Fall 2020), Class 1: Introduction

Programming for AI 1:44:45

Programming for AI (AI504, Fall 2023), Class 7: Convolutional Neural Network

Programming for AI 1:39:51

Programming for AI (AI504, Fall 2020), Class 11: Transformer

Programming for AI 1:29:46

Programming for AI (AI504, Fall 2023), Practice 1: Numpy

Programming for AI 0:43:24

Programming for AI (AI504, Fall 2023), Project 1 Announcement

Programming for AI 1:31:18

Programming for AI (AI504, Fall 2022), Class 3: Logistic Regression & Neural Networks

Programming for AI 2:02:16

Programming for AI (AI504, Fall 2023), Class 11: BERT & GPT

Programming for AI 1:08:41

Programming for AI (AI504, Fall 2023), Practice 7: Convolutional Neural Network

Programming for AI 1:29:43

Programming for AI (AI504, Fall 2022), Class 5: Variational Autoencoder

Комментарии
Автор

Thank you so much for this tutorial!! It is so helpful. For anyone interested out there. I experimented changing the width and length of the NN architecture. I obtained the best results by increasing the width of the NN. Changing the length did not help to obtain better results.

sebastiangutierrez
Автор

Can we have access to the notebook, please?

leninrafaelrierasegura
Автор

is "t[:batch_time]" in get_batch correct? shouldn't we get the corresponding time points from `t` instead of a constant first `batch_time` elements from t?

metaseq
Автор

Why in the forward method of ODEFunc do you have self.net(y**3)? Why not just self.net(y) since y is the input to the network?

chadwinters
Автор

Wow, this is a really wonderful resource and tutorial. Thanks so much posting it. Is it possible to provide a link to the Colab notebook, so that others can work through the code? Thanks again.

krishnabhogaonker