Generative Models — Deep Learning & Neural Networks Roadmap
Architectures designed to generate new data rather than just classify it
Steps in Generative Models
- Autoencoders — advanced · Compressing data into a latent representation and reconstructing it
- Variational Autoencoders (VAEs) — advanced · Learning a probabilistic latent space that supports sampling new data
- Generative Adversarial Networks (GANs) — advanced · A generator and discriminator trained adversarially to produce realistic data
- Diffusion Models Basics — advanced · Generating data by learning to reverse a gradual noising process
- Applications of Generative Models — advanced · Image generation, style transfer, data augmentation and synthetic data use cases
Part of
- Deep Learning & Neural Networks roadmap — the full learning path