Generative Adversarial Networks (GANs) in Practice

With Introductory Review on Artificial Neural Networks and Deep Learning Algorithms and Models

Deep learning is one of the most recent and advanced topics in machine learning, with several applications in many fields. It shows promising results in many areas, from computer vision to drug discovery and stock market prediction. There are many books and articles in deep learning that discuss its algorithms, theories, and applications. Also, because of its capabilities and potentials in solving different problems by deploying different data types, many researchers and people who are not in computer science or related fields are interested in learning and using deep learning architectures in their projects.

What you’ll learn

  • The fundamentals of Artificial Neural Networks (ANNs) and reviews state-of-the-art DL examples..
  • The fundamental of Deep learning and the most popular algorithms..
  • The most popular GAN algorithms features and requirements ..
  • How to implement a GAN model in PRACTICE..
  • Several examples and applications of GAN..

Course Content

  • Introduction –> 1 lecture • 7min.
  • Machine Learning –> 10 lectures • 38min.
  • Artificial Neural Networks –> 6 lectures • 22min.
  • Deep Learning –> 7 lectures • 26min.
  • Generative Adversarial Networks –> 7 lectures • 17min.
  • GAN for MNIST and FASHION –> 6 lectures • 30min.
  • Conditional GAN –> 4 lectures • 15min.
  • Cycle GAN –> 1 lecture • 3min.

Generative Adversarial Networks (GANs) in Practice

Requirements

  • Probability,.
  • Calculus,.
  • Basic of Python, Tensor Flow, Keras, and Numpy..

Deep learning is one of the most recent and advanced topics in machine learning, with several applications in many fields. It shows promising results in many areas, from computer vision to drug discovery and stock market prediction. There are many books and articles in deep learning that discuss its algorithms, theories, and applications. Also, because of its capabilities and potentials in solving different problems by deploying different data types, many researchers and people who are not in computer science or related fields are interested in learning and using deep learning architectures in their projects.

 

This course gives you some fundamentals of artificial neural networks and deep learning and then has focused on Generative Adversarial Network and its applications with some coding examples to understand the concepts better. The course is suitable for people who are new in the machine learning field and deep learning and would like to learn how to implement deep learning algorithms (especially GAN algorithms) using python, TensorFlow, and Keras.

 

The course has seven chapters and starts with some fundamentals in machine learning concepts and end with some idea in CycleGAN. Each chapter has some quizzes and assignments to test students learning. It also provides the solution for each project.

 

I would expect this course’s contents to be welcomed worldwide by undergraduate and graduate students and researchers in deep learning, including practitioners in academia and industry.