22557e7132
- 7-8월 초기 구축 문서 12개를 _archive/troubleshooting/2025_07-08_initial_setup/로 이동 - book/300_architecture/390_human_in_the_loop_intent_learning.md를 journey/research/intent_classification/로 이동 (개발 여정 문서) - 빈 폴더 제거 (journey/assets/*)
723 B
723 B
CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms
- Authors: Ahmed Elgammal, Bingchen Liu, Mohamed Elhoseiny, Marian Mazzone
- Year: 2017
- Summary: This paper presents the Creative Adversarial Network (CAN), a modification of GANs designed to generate creative art. The generator is trained to produce novel works that do not conform to established art styles, while the discriminator learns to distinguish between established styles and the generated works. The system is driven by a dual objective: to create something that is art, but is also novel and stylistically different from what it has seen.
- Link: https://arxiv.org/abs/1706.07068