generative-deep-learning

KO | EN

gitlite — search

#python #java #python3 #arduino #golang #machine-learning #rust #html #flask #javascript #seismology #nodejs

generative-deep-learning

★ 11 Open GitHub ↗

Code repository for the PhD course of "Generative Deep Learning" 2022

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Generative Deep Learning
![](https://img.shields.io/badge/TensorFlow%20Faculty%20Award-2021%20Winner-orange.svg)

Code repository for the PhD course of [**Generative Deep Learning**](https://danilocomminiello.site.uniroma1.it/teaching/gdl), 3 CFU (18 hours), edition 2021/2022.

Instructor: Prof. Danilo Comminiello :man_teacher:

## News 💣
We have the pleasure to host two webinars from international experts in the generative deep learning research field!

We will host **[Chitwan Saharia](https://chitwansaharia.github.io/)** from Google Brain and **[Yang Song](https://yang-song.github.io/)** from Stanford AI Lab!

## About the course :dart:

This course covers the foundations and the main models of generative deep learning, including autoregressive models, variational autoencoders, generative adversarial networks, flow-based models and energy-based models.

#### Program at a glance :page_with_curl:

* **INTRODUCTION TO GENERATIVE DEEP LEARNING.** Generative modeling and probabilistic generative models. Deep neural networks. Building deep network models. Learning latent representations.
* **GENERATIVE AUTOREGRESSIVE MODELS.** Autoregressive models. Parameterization by neural networks. Generation examples.
* **VARIATIONAL AUTOENCODERS.** Probabilistic principal component analysis. Variational inference. Variational autoencoders (VAEs) and modern deep VAE architectures.
* **GENERATIVE ADVERSARIAL NETWORKS.** Generator and critic. Training generative adversarial networks (GANs). Optimization and loss functions of GANs.
* **ENERGY-BASED AND DIFFUSION MODELS.** Likelihood based learning. Energy based models (EBMs) with latent variables. Self-supervised learning with EBMs. Diffusion and score-based models.
* **APPLICATIONS.** Python examples of generative deep learning models, including: music generation, image style transfer, text generation, video generation, anomaly detection, data augmentation, inverse problems solution and medical imaging applications, among others.
* **SEMINARS.**

## Seminars with special guests :technologist:

* **Imagen: imagine · illustrate · inspire**, a webinar from **[Chitwan Saharia](https://chitwansaharia.github.io/)**, Google Brain.

Tuesday 21st, 4:00 pm, [Zoom Link](https://uniroma1.zoom.us/j/86596351314?pwd=T0pja1RKLzFTd2ZabWN0TS9yN2tMQT09).

* **Creating noise from data is easy; creating data from noise is generative modeling**, a webinar from **[Yang Song](https://yang-song.github.io/)**, Stanford AI Lab.

Monday 27th, 5:30 pm, [Zoom Link](https://uniroma1.zoom.us/j/86596351314?pwd=T0pja1RKLzFTd2ZabWN0TS9yN2tMQT09).

## About the repository :desktop_computer:

This repository contains the material to reproduce and attend the Generative Deep Learning course.
* :books: The folder `Slides` includes the slides of the lectures.
* :computer: The folder `Notebooks` contains Python notebooks and tutorials carried out in TensorFlow.
* :office_worker: The folder `Seminars` comprises material from course seminars.
* :busts_in_silhouette: The folder `Projects` will collect students exam project.

### Projects :soon:

Coming soon...

## References

For more information please contact the instructor or visit:
* [Course page](https://danilocomminiello.site.uniroma1.it/teaching/gdl).
* [Classroom page](https://classroom.google.com/u/0/c/NDIyNzY2MjYxNDY5), course code: rg2mczw.

generative-deep-learning

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README