DeepLearning.AI - Build Basic Generative Adversarial Networks (GANs)
- Offered byCoursera
Build Basic Generative Adversarial Networks (GANs) at Coursera Overview
Duration | 31 hours |
Total fee | Free |
Mode of learning | Online |
Difficulty level | Intermediate |
Official Website | Explore Free Course  |
Credential | Certificate |
Build Basic Generative Adversarial Networks (GANs) at Coursera Highlights
- This Course Plus the Full Specialization.
- Shareable Certificates.
- Graded Programming Assignments.
Build Basic Generative Adversarial Networks (GANs) at Coursera Course details
- In this course, you will:
- - Learn about GANs and their applications
- - Understand the intuition behind the fundamental components of GANs
- - Explore and implement multiple GAN architectures
- - Build conditional GANs capable of generating examples from determined categories
- The DeepLearning.AI Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques through an easy-to-understand approach. It also covers social implications, including bias in ML and the ways to detect it, privacy preservation, and more.
- Build a comprehensive knowledge base and gain hands-on experience in GANs. Train your own model using PyTorch, use it to create images, and evaluate a variety of advanced GANs.
- This Specialization provides an accessible pathway for all levels of learners looking to break into the GANs space or apply GANs to their own projects, even without prior familiarity with advanced math and machine learning research.
Build Basic Generative Adversarial Networks (GANs) at Coursera Curriculum
Week 1: Intro to GANs
Welcome to the Specialization
Welcome to Week 1
Generative Models
Real Life GANs
Intuition Behind GANs
Discriminator
Generator
BCE Cost Function
Putting It All Together
(Optional) Intro to PyTorch
Syllabus
Connect with your mentors and fellow learners on Slack!
Check out some non-existent people!
Pre-trained Model Exploration
Inputs to a Pre-trained GAN
Works Cited
How to Refresh your Workspace
Week 2: Deep Convolutional GANs
Welcome to Week 2
Activations (Basic Properties)
Common Activation Functions
Batch Normalization (Explained)
Batch Normalization (Procedure)
Review of Convolutions
Padding and Stride
Pooling and Upsampling
Transposed Convolutions
(Optional) A Closer Look at Transposed Convolutions
(Optional) The DCGAN Paper
(Optional Notebook) GANs for Video
Works Cited
Week 3: Wasserstein GANs with Gradient Penalty
Welcome to Week 3
Mode Collapse
Problem with BCE Loss
Earth Mover?s Distance
Wasserstein Loss
Condition on Wasserstein Critic
1-Lipschitz Continuity Enforcement
(Optional Notebook) ProteinGAN
(Optional) The WGAN and WGAN-GP Papers
(Optional) WGAN Walkthrough
Works Cited
Week 4: Conditional GAN & Controllable Generation
Welcome to Week 4
Conditional Generation: Intuition
Conditional Generation: Inputs
Controllable Generation
Vector Algebra in the Z-Space
Challenges with Controllable Generation
Classifier Gradients
Disentanglement
Conclusion of Course 1
(Optional) The Conditional GAN Paper
(Optional) An Example of a Controllable GAN
Works Cited
Acknowledgments
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?
Data ScienceMachine LearningMachine Learning and Pattern RecognitionBuild Basic Generative Adversarial Networks (GANs)