Compare a generator-discriminator game and a diffusion process without confusing statistical creation with intention.
Proof of success: explain "Generate and denoise: GANs and diffusion", complete "Three-Level Denoising" and name the limit of the analogy.
In the pattern workshop, a generator proposes cards and a discriminator tries to tell real from proposed cards apart: this opposition describes a GAN. In another experiment, we progressively add noise to the cards, then a network learns to reverse small noise steps: that's the idea of diffusion. Both families learn distributions of examples; they don't choose a message or a truth.
Preview — the rest of the lesson is for enrolled readers.
Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.
Sign inNo account yet? Create oneThe first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.