From GAN to WGAN

📰 Lilian Weng's Blog

Wasserstein GAN improves training of generative adversarial networks by using a smooth metric to measure distance between probability distributions

advanced Published 20 Aug 2017
Action Steps
  1. Understand the maths behind GAN models
  2. Identify challenges in training GANs
  3. Learn about Wasserstein GAN and its smooth metric
  4. Implement WGAN to improve model training
Who Needs to Know This

Machine learning researchers and engineers on a team can benefit from understanding the maths behind GANs and WGANs to improve model training and performance

Key Insight

💡 Wasserstein GAN adopts a smooth metric to measure distance between probability distributions, improving training

Share This
💡 WGAN improves GAN training with smooth metric
Read full article → ← Back to News