Course Outline

Introduction

GANs and Variational Autoencoders

  • What is a GAN? What are variational autoencoders?
  • GAN and variational autoencoders architecture

Preparing the Development Environment

  • Instaling and configuring TensorFlow

Generative Models

  • Sampling data
  • Working with Bayes Classifier and Gaussian mixture model

Variational Autoencoders

  • Parameterizing and reparameterizing with neural networks
  • Finding dimensionality reduction
  • Visualizing latent space

GANs

  • Implementing backward propagation
  • Working with loss functions
  • Training a classifier model
  • Generating new data

Advanced GANs

  • Working with conditional GAN
  • Working with deep convolutional GAN
  • Working with progressive GAN

Summary and Conclusion

Requirements

  • Python programming experience

Audience

  • Data Scientists
  14 Hours
 

Number of participants


Starts

Ends


Dates are subject to availability and take place between 09:30 and 16:30.
Open Training Courses require 5+ participants.

Related Courses

Related Categories