GAN

الشبكة التوليدية التنافسية

بنية توليدية تتكون من مُولِّد ومُميِّز يتنافسان: المُولِّد يحاول إنتاج بيانات واقعية والمُميِّز يحاول كشف المزيّف، فيتحسن كلاهما.

A generative architecture consisting of a generator and discriminator that compete: the generator tries to produce realistic data and the discriminator tries to detect fakes, both improving in the process.

Also translated asالشبكة التنافسية، شبكة GAN

First appears in this corpus in: Pixel Recurrent Neural Networks (2016)

Appears in these papers

Diffusion Models Beat GANs on Image Synthesis2021 in the sky ✦
ELECTRA: Pre-Training Text Encoders as Discriminators Rather Than Generators2020 in the sky ✦
High-Resolution Image Synthesis with Latent Diffusion Models2022 in the sky ✦
Image-to-Image Translation with Conditional Adversarial Networks2017 in the sky ✦
Pixel Recurrent Neural Networks2016 in the sky ✦
Generative Modeling by Estimating Gradients of the Data Distribution2019 in the sky ✦