Beginner · Generative AI
Discriminator
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. A system that identifies whether input data is real or fake, often used within generative adversarial networks.
Technical Definition
A system that identifies whether input data is real or fake, often used within generative adversarial networks.
How it works
In machine learning, a discriminator is a component, often a neural network, that is trained to classify input data as either authentic or synthetic. In the context of Generative Adversarial Networks (GANs), the discriminator works in tandem with a generator, receiving both real data and generator-created data. Its role is to distinguish between the two, providing feedback to the generator to improve its ability to produce realistic outputs.
Related Concepts
- Generative Adversarial Network (GAN) — Two neural networks — a generator and discriminator — compete against each other to produce increasingly realistic synthetic data.
- GAN — Abbreviation for Generative Adversarial Network, a class of machine learning frameworks.
- Generator — The component of a Generative Adversarial Network (GAN) responsible for creating new, synthetic data samples.