generative adversarial network
Sign in to saveAlso known as GAB, GAN
deep learning method in which two neural networks compete with each other in a game, learning to generate new data with the same statistics as the training set
Research
6,386 papers- Generative adversarial network in medical imaging: A review.Medical image analysis · 2019
- Spiking generative adversarial network with attention scoring decoding.Neural networks : the official journal of the International Neural Network Society · 2024
- Generative Adversarial Network (GAN) for Simulating Electroencephalography.Brain topography · 2023
- A review of generative adversarial network applications in optical coherence tomography image analysis.Journal of optometry · 2022
- Generative adversarial network based synthetic data training model for lightweight convolutional neural networks.Multimedia tools and applications · 2023
via PubMed
Wikidata facts
- Subclass of
- algorithm
- Image
- CRAIYON-REALESRGAN-A professional painting of teachers screaming at students about citations in a classroom.jpg
Show 5 more facts
- discoverer or inventor
- Ian J. Goodfellow
- short name
- RGA
- Commons category
- Generative adversarial networks
- Stack Exchange tag
- ai.stackexchange.com/tags/generative-adversarial-networks
- time of discovery or invention
- 2014-06-10
Sources (7)
via Wikidata · CC0
~40 min read
Encyclopedic overview
An illustration of how a GAN works
A generative adversarial network (GAN) is a class of machine learning frameworks and a prominent framework for approaching generative artificial intelligence. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014. In a GAN, two neural networks compete with each other in the form of a zero-sum game, where one agent's gain is another agent's loss.
Excerpted from Wikipedia’s “generative adversarial network” article, available under the CC BY-SA 4.0 licence.