Diffusion models are a class of generative models that learn data distributions by iteratively adding and removing noise from data. They have gained prominence for their ability to generate high-quality samples in domains like image and audio synthesis.
Courses
A Variational Autoencoder (VAE) is a generative model that uses neural networks to encode input data into a latent space and then decodes it back to reconstruct the original data. VAEs combine principles from deep learning and probabilistic graphical models, enabling unsupervised learning of complex data distributions.