深度生成模型
Deep Generative Models
| 節 | 週三 |
|---|---|
2 09:00–09:50 | 深度生成模型 CM218 3 節連堂 |
3 10:10–11:00 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
Generative models are a method in AI and machine learning that are widely used in various fields, in particular, generative AI such as large language models. They can serve as a foundational approach, used in conjunction with other algorithms, for example, as part of data augmentation, or they can simply be used to generate more content. In recent years, there have been many advances in generative models due to the development of deep learning, such as Diffusion models, GANs, VAEs, autoregression models, Generative flow, and so on. In this course, we will start with an introduction to these foundational models and then proceed to cover some of the latest developments.
Deep learning, linear algebra
course website https://tjwei.tw/
homework 100%
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction |
| 第 2 週 | Introduction: Autoencoder |
| 第 3 週 | Introduction: Autoregressive model |
| 第 4 週 | Introduction: n-gram and language generalization |
| 第 5 週 | VAE: Variational Autoencoder |
| 第 6 週 | GAN: GAN, DCGAN and math |
| 第 7 週 | GAN: WGAN and SNGAN |
| 第 8 週 | Conditional GAN |
| 第 9 週 | Pix2Pix and CycleGAN |
| 第 10 週 | Diffusion Model, Generative Flow |
| 第 11 週 | Diffusion Model. Theory and Stochastic Differential Equation |
| 第 12 週 | Diffusion Model and Language Model |
| 第 13 週 | Generative Language models: Applications and Theory |
| 第 14 週 | Generative Language models: Implementations |
| 第 15 週 | Recent advances |
| 第 16 週 | Summary and review |
online