AI engineering glossary · Generative media multimodal
What is WGAN (Wasserstein GAN)?
Wasserstein GAN (also called WGAN): A GAN variant that replaces the usual loss with an estimate of the Wasserstein (earth mover's) distance between real and generated distributions, using a critic constrained to be smooth. It gives more stable training and a loss that tracks sample quality.
Wasserstein GAN: an example
Training a WGAN, the critic's loss falls steadily as images improve, unlike the noisy loss of a standard GAN.
Related terms
More Generative media multimodal terms
- Watermarking generated content
- wav2vec 2.0
- WaveNet
- Whisper
- Zero-shot TTS
- 3D Gaussian splatting
- Acoustic model
- Audio language model
Where you learn it
Wasserstein GAN is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.