생성형 AI
“이것은 무엇인가”의 판별에서 “어떤 모습이어야 하는가”의 합성으로
OVERVIEW
- 전체 항목
- 6
- 입문
- 2
- 중급
- 3
- 고급
- 1
A generative model is not content with labelling a sample; it must produce the sample itself. Autoencoders, GANs, diffusion models and autoregressive models are four principal routes, each giving a precise mathematical formulation to the vague goal of “looking real” — and each now underpinning image, video, speech and 3D content production.
이 영역이 답하는 질문
- Q1
What distribution is a generative model learning?
- Q2
Why is diffusion more stable than a GAN?
- Q3
How does a text prompt become an image?