AI Jargon Buster
AI news and the language around it, simplified.
What is a Generative Adversarial Network (GAN)?
A Generative Adversarial Network is a type of AI architecture where two neural networks compete against each other to create highly realistic data. One network, known as the generator, tries to create fake content like images or audio. The other network, the discriminator, acts as a critic that tries to distinguish the fake content from real-world examples. Through this constant back-and-forth, the generator gets progressively better at creating content that is nearly indistinguishable from reality. Think of it like a master art forger trying to fool an expert museum curator. The forger keeps refining their technique until the curator can no longer tell the difference between the fake and the original. This process allows the system to learn the patterns and structures of complex data without needing human guidance.
Why this matters to you
GANs are the technology behind many of the hyper-realistic images and videos you see online, including synthetic media and high-quality digital art. In a workplace, understanding this technology is important for recognizing how easily digital assets can be faked or manipulated. This has significant implications for media authenticity, cybersecurity, and creative workflows where verifying the source of an image or video is essential for maintaining professional trust.
How you might hear this
Our design team is exploring how we might use a Generative Adversarial Network to create unique product mockups for our upcoming marketing campaign.
AI Jargon Buster
Search any AI term, explained in plain English.
Type a term below and search. You will be taken straight to the tool.
Related terms
See how your CV performs against the ATS algorithms that screen candidates before a human ever reads your application.
Try the CV Optimiser →How AI job displacement actually works, what it means for your career, and what to do about it. Written by someone who has been in recruitment for 25 years.
When the Ground Shifts →