GAN
Definition
Generative Adversarial Network. A framework with two neural networks, a generator that creates synthetic data and a discriminator that tries to distinguish it from real data. They train together in an adversarial loop until the generator's output is difficult to separate from genuine content.
Related terms
- Diffusion model
- A generative neural network architecture (Ho et al., 2020; Stable Diffusion, Rombach et al., 2022) that learns to reverse a noise-addition process...
- Encoder-decoder
- A neural architecture where an encoder compresses an input into a compact latent representation and a decoder reconstructs an output image from...
- Latent space
- The compressed, lower-dimensional representation of data learned by a neural network's internal layers. Generative models sample from or navigate this space to...
- NeRF (Neural Radiance Field)
- A neural representation that encodes a 3-D scene as a continuous volumetric function, allowing novel viewpoints to be rendered. In talking-head systems,...
- Voice conversion
- Transforming the timbre and identity of one speaker's voice to match another while preserving the linguistic content. Used in voice-cloning attacks to...
Explained in
- Deepfake Generation: GANs, Diffusion, and Face-Swap PipelinesGenerative Adversarial Network. A framework with two neural networks, a generator that creates synthetic data and a discriminator that tries to distinguish it...