What are GANs and VAEs?

GANs (Generative Adversarial Networks) and VAEs (Variational Autoencoders) are generative models used to create new data samples. GANs use a generator-discriminator setup, while VAEs rely on probabilistic encoding and decoding.

What are GANs and autoencoders?

GANs generate realistic data by pitting two networks against each other, while autoencoders compress and reconstruct data. Both are used in unsupervised learning but serve different purposes in data generation and feature learning.

What is the introduction of autoencoders?

Autoencoders are neural networks designed to learn efficient data representations by encoding input into a compressed form and then decoding it back to reconstruct the original input.

What is the difference between VAEs and autoencoders?

Standard autoencoders compress data deterministically, while VAEs introduce randomness through probabilistic encoding, allowing them to generate new data samples similar to the original.

What are different types of autoencoders?

Common types include vanilla autoencoders, sparse autoencoders, denoising autoencoders, variational autoencoders (VAEs), and convolutional autoencoders—each suited for specific learning tasks.

When will I have access to the lectures and assignments?

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

What will I get if I subscribe to this Specialization?

When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Is financial aid available?

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

Introduction Course to Autoencoders, VAEs, and GANs

Introduction Course to Autoencoders, VAEs, and GANs

This course is part of Generative AI Models and Transformer Networks Certification Specialization

Instructor: Priyanka Mehta

Included with

Learn more

2 modules

Gain insight into a topic and learn the fundamentals.

Beginner level

Recommended experience

4 hours to complete

Flexible schedule

Learn at your own pace

2 modules

Gain insight into a topic and learn the fundamentals.

Beginner level

Recommended experience

4 hours to complete

Flexible schedule

Learn at your own pace

What you'll learn

Build and train Autoencoders and VAEs using TensorFlow
Use VAEs for generating synthetic data like images
Understand and apply GAN architecture and training techniques
Create realistic outputs with GANs for real-world use cases

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

7 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the Generative AI Models and Transformer Networks Certification Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 2 modules in this course

This deep learning course provides a comprehensive introduction to Autoencoders, Variational Autoencoders (VAE), and Generative Adversarial Networks (GANs). Begin by exploring how autoencoders compress and reconstruct data, and discover how VAEs add probabilistic modeling to enhance generative capabilities. Learn the VAE training process and implement a VAE using TensorFlow for image generation with the MNIST dataset. Progress to mastering GANs—understand their adversarial training approach, how the generator and discriminator interact, and explore real-world applications. Gain hands-on experience by building a GAN to generate realistic fake images through step-by-step demos.

To be successful in this course, you should have a basic understanding of neural networks, machine learning concepts, and Python programming. By the end of this course, you’ll be able to: - Implement and train autoencoders and VAEs - Apply VAEs for generative tasks like image synthesis - Build and train GANs to generate realistic data - Understand and apply adversarial training in real-world use cases Ideal for aspiring AI developers, ML engineers, and data scientists exploring generative deep learning.

Module details

Explore the fundamentals of Autoencoders and Variational Autoencoders (VAE) in this module. Learn how autoencoders compress and reconstruct data, the challenges they face, and how VAEs overcome them. Understand the VAE training process and its generative capabilities. Gain hands-on experience by implementing a VAE with TensorFlow for image generation using the MNIST dataset.

What's included

8 videos1 reading4 assignments

8 videosTotal 46 minutes

Learning Objectives1 minute
Autoencoders6 minutes
Challenges in Autoencoders3 minutes
Introdution to Variational Autoencoders6 minutes
VAE Generative Training Process5 minutes
Steps Involved in VAE4 minutes
Image Generation5 minutes
Demo: Implementing a VAE with TensorFlow for Image Generation Using the MNIST Dataset16 minutes

1 readingTotal 10 minutes

Course Syllabus 10 minutes

4 assignmentsTotal 85 minutes

Assessment for Autoencoders and Variational Autoencoders (VAE)40 minutes
Quiz on Introduction to Autoencoders15 minutes
Quiz on VAE Training Process15 minutes
Quiz on VAE Generative Applications15 minutes

Master Generative Adversarial Networks (GANs) in this hands-on module. Learn how GANs work through their unique adversarial training process and explore real-world use cases across industries. Understand generator-discriminator dynamics and how they produce realistic data. Gain practical skills by implementing a GAN to generate fake images with guided demos and code examples.

What's included

4 videos3 assignments

4 videosTotal 25 minutes

Introduction to GANs5 minutes
Training Process and Industrial Use Case of GAN6 minutes
Demo: Generating Fake Images with Generative Adversial Networks (GANs)13 minutes
Key Takeaways1 minute