A GAN (Generative Adversarial Network) was called out as the ‘most interesting idea in ML in the last 10 years’
Think of them as a model that can generate new content.
It has 2 networks – a generator and a discriminator.
The generator creates fake samples and tries to fool the discriminator into believing that they are real.
The discriminator will try to detect the generated samples from both the real and fake samples.
A lot of attention garnered is due to its interesting applications – say, generating synthetic data, image to image translation and yes, anime.
Though concerns abound around security and potential for malicious intent, Generative AI is part of Gartner’s Top Technology Trends 2022
“By 2025, generative AI will account for 10% of all data produced, from less than 1% today”
While we wait for more synthetic data, here is an anime of mine created on AnimeGANv2
(‘You look like a funny cartoon character’ was my 6 yo’s take)
********************************************
#GAN #AI #GenerativeAI
#reviewswithranjani