Want to learn more?
Explore: What Generative AI Means for Business
Learn: Gartner Experts Answer the Top Generative AI Questions for Your Enterprise
Download: Create Your AI Strategy Workbook
Discover: Featured Business Insights and Trends
- Gartner client? Log in for personalized search results.
Generative Adversarial Networks (GANs)
Generative adversarial networks (GANs) are used after training to generate totally novel media content, synthetic data, and models of physical objects that preserve the likeness of the original data. GANs are composed of two neural networks: one — called the generator — specializes in generating objects of a specific type (e.g., images of human faces or dogs, or models of molecules); the other — the discriminator — learns to evaluate them as real or fake.
Recommended Content for You
Attend a Conference
Experience Enterprise Architecture conferences
With exclusive insight from Gartner experts on the latest trends, sessions curated for your role and unmatched peer networking, Gartner conferences help you accelerate your priorities.
22 – 24 Sep 2025
Gartner CIO & IT Executive Conference
São Paulo, Brazil
