The most important one, in my opinion, is adversarial training (also called GAN for Generative Adversarial Networks). This is an idea that was originally proposed by Ian Goodfellow when he was a student with Yoshua Bengio at the University of Montreal (he since moved to Google Brain and recently to OpenAI).
This, and the variations that are now being proposed is the most interesting idea in the last 10 years in ML, in my opinion.Yann LeCun 认为 GAN 很可能会给深度学习模型带来新的重大突破,是20年来机器学习领域最酷的想法。这几年 GAN 发展势头非常强劲。下面这张图是近几年 ICASSP 会议上所有提交的论文中包含关键词 “generative”、“adversarial” 和 “reinforcement” 的论文数量统计。
欢迎光临 黑马程序员技术交流社区 (http://bbs.itheima.com/) | 黑马程序员IT技术论坛 X3.2 |