The Generative Adversarial Network (GAN) is a method to train and optimize AI-algorithms. A GAN consists of two components, the "generator" and the "discriminator". Let's take the example of an AI-algorithm that generates images; in this scenario the "generator" tries to produce pictures in the painting style of Picasso, for example. The "discriminator" evaluates these results and rejects them - or accepts them. A feedback loop for training purposes is established.

Only recently sites went viral that generated fake portraits, that is: computer-generated portraits that look amazingly real. But these people do not exist, compare: ThisPersonDoesNotExist.com. This is the method of the "Generative Adversarial Networks".

Author

Sebastian Zang has cultivated a distinguished career in the IT industry, leading a wide range of software initiatives with a strong emphasis on automation and corporate growth. In his current role as Vice President Partners & Alliances at Beta Systems Software AG, he draws on his extensive expertise to spearhead global technological innovation. A graduate of Universität Passau, Sebastian brings a wealth of international experience, having worked across diverse markets and industries. In addition to his technical acumen, he is widely recognized for his thought leadership in areas such as automation, artificial intelligence, and business strategy.