Master GANs across various levels, from foundational principles to advanced applications in computer vision, NLP, and audio processing.

Hands-On Generative Adversarial Networks with Keras (1).png

mbe-2.tar.gz

abcds

abcd

mbe2

This course focuses on generative adversarial networks (GANs), which have reshaped machine learning and deep learning landscapes. This course also aims to provide a comprehensive introduction to GANs, starting with a deep dive into deep learning and generative models and their extensive applications in artificial intelligence.

You will start by getting an overview of deep learning and generative models. You will then explore the wide-ranging applications where GANs can be utilized. You will get hands-on experience in constructing, evaluating, and enhancing GANs. You’ll also learn how to train GANs for high-resolution image generation, implement conditional GANs for output control, and adopt progressive training methods to refine GAN performance. 

After completing this course, you will have a good understanding of the latest advancements within the GAN frameworks used in computer vision, natural language processing (NLP), and audio processing.

Hands-On Generative Adversarial Networks with Keras

Get familiar with the application of Jensen-Shannon divergence (JSD) and the Kolmogorov-Smirnov (KS) two-sample test in comparing real and GAN-generated samples.

Getting Started

Deep Learning Basics and Environment Test

Introduction to Generative Models

Implementing Our First GAN

Evaluating Our First GAN

Improving Our First GAN

Synthesizing and Manipulating Images with GANs

Progressive Growing of GANs

Generation of Discrete Sequences Using GANs

Text-to-Image Synthesis with GANs

Speech Enhancement with GANs

TequilaGAN—Identifying GAN Samples

What’s Next in GANs

Conclusion

Appendix

Metrics

Jensen-Shannon divergence (JSD)