Build Basic Generative Adversarial Networks (GANs)
- 4.7
-
![]()
![]()
![]()
![]()
![]()
Approx. 31 hours to complete
Course Summary
Learn to build basic generative adversarial networks (GANs) in this course. Gain hands-on experience in working with GANs and use them to generate images and music.Key Learning Points
- Learn the basics of GANs and how they work
- Build your own GANs using TensorFlow
- Create and generate images and music using GANs
Related Topics for further study
Learning Outcomes
- Understand the fundamentals of GANs
- Build your own GANs using TensorFlow
- Create and generate images and music using GANs
Prerequisites or good to have knowledge before taking this course
- Basic knowledge of Python programming
- Familiarity with machine learning concepts
Course Difficulty Level
IntermediateCourse Format
- Online
- Self-paced
Similar Courses
- Generative Adversarial Networks (GANs) Specialization
- Deep Learning Specialization
Related Education Paths
Notable People in This Field
- Ian Goodfellow
- Yann LeCun
Related Books
Description
In this course, you will:
Outline
- 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
Summary of User Reviews
Learn how to build basic Generative Adversarial Networks (GANs) with this course on Coursera. Students have praised the course for its clear explanations and hands-on approach. Overall, the course has received positive feedback from users.Key Aspect Users Liked About This Course
Hands-on approach to learningPros from User Reviews
- Clear explanations of complex concepts
- Great practical exercises
- Engaging instructor
- Good pacing of lessons
- Useful resources provided
Cons from User Reviews
- Some concepts may be too advanced for beginners
- Lack of depth in some areas
- Not enough examples provided
- Limited interaction with the instructor
- Some technical issues with the platform
Sharon Zhou
4.7 Raiting
Complete Tensorflow 2 and Keras Deep Learning Bootcamp
- 4.7
-
![]()
![]()
![]()
![]()
![]()
Learn to use Python for Deep Learning with Google's latest Tensorflow 2 library and Keras! 0's official API) to quickly and easily build models....
TensorFlow 2.0 Practical Advanced
- 4
-
![]()
![]()
![]()
![]()
![]()
Master Tensorflow 2. 0, Google’s most powerful Machine Learning Library, with 5 advanced practical projects Google has recently released TensorFlow 2....
Introduction to Deep Learning
- 4.5
-
![]()
![]()
![]()
![]()
![]()
The goal of this course is to give learners basic understanding of modern neural networks and their applications in computer vision and natural language understanding....
Build Decision Trees, SVMs, and Artificial Neural Networks
- 0.0
-
![]()
![]()
![]()
![]()
![]()
There are numerous types of machine learning algorithms, each of which has certain characteristics that might make it more or less suitable for solving a particular problem....
