14 hours





Course features:


Lab Requirements:

Learning Path

  • Overview of generative artificial intelligence and its applications
  • Types of generative AI models: GANs, VAEs, and autoregressive models
  • Understanding the differences between generative and discriminative models
  • In-depth exploration of GANs architecture and training procedure
  • Understanding the generator and discriminator networks
  • Applications of GANs in image generation, style transfer, and data augmentation
  • Introduction to variational autoencoders (VAEs) architecture and objective function
  • Understanding reconstruction loss and KL divergence
  • Applications of VAEs in image generation, anomaly detection, and dimensionality reduction
  • Participants implement and train GAN and VAE models using TensorFlow or PyTorch
  • Generating new images and analyzing latent space representations
  • Fine-tuning hyperparameters and architecture for improved performance
  • Overview of autoregressive models architecture and training procedure
  • Understanding autoregressive models for sequential data generation
  • Advanced techniques and architectures for generative modeling
  • Introduction to conditional generative models such as conditional GANs and conditional VAEs
  • Understanding conditional image generation and text-to-image synthesis
  • Hands-on exercise: implementing conditional generative models for specialized tasks
  • Exploring advanced applications of generative AI in various domains
  • Case studies and examples of generative AI applications in healthcare, art, gaming, and more
  • Emerging trends and future directions in generative AI research
  • Participants work on advanced generative AI projects and applications
  • Implementing custom generative models for specific use cases
  • Experimenting with cutting-edge techniques and architectures in generative AI