Generative Adversarial Network
A framework where two neural networks compete — a generator creates fake data and a discriminator tries to tell real from fake. This adversarial process drives both networks to improve, producing increasingly realistic outputs.
Why It Matters
GANs pioneered realistic image generation and are still used for data augmentation, style transfer, and super-resolution. They laid groundwork for the generative AI revolution.
Example
A GAN generating realistic human faces that do not belong to real people (as seen on thispersondoesnotexist.com), with the generator and discriminator improving in tandem.
Think of it like...
Like a counterfeiter and a detective in an arms race — the counterfeiter gets better at making fakes, the detective gets better at spotting them, and both improve together.
Related Terms
Generative AI
AI systems that can create new content — text, images, music, code, video — rather than just analyzing or classifying existing data. These models learn patterns from training data and generate novel outputs that resemble the original data.
Diffusion Model
A type of generative AI model that creates data by starting with random noise and gradually removing it, step by step, until a coherent output (like an image) emerges. This process is called denoising.
Deep Fake
AI-generated media (especially video and audio) that convincingly depicts real people saying or doing things they never actually said or did. Created using deep learning techniques.