Academy of Mathematics and Systems Science, CAS
Colloquia & Seminars
| | Speaker: | 朱占星 博士, 北京大学数学学院
| | Inviter: | 明平兵 研究员 | Title:
| Adversarial Training for Deep Learning: A General Framework for Improving Robustness and Generalization | Time & Venue:
| 2019.09.19 10:00-11:00 N202 | Abstract:
| Deep learning has achieved tremendous success in various application areas, such as computer vision, natural language processing, game playing (AlphaGo), etc. Unfortunately, recent works show that an adversary is able to fool the deep learning models into producing incorrect predictions by manipulating the inputs maliciously. The corresponding manipulated samples are called adversarial examples. This vulnerability issue dramatically hinders the deployment of deep learning, particularly in safety-critical applications. In this talk, I will introduce various approaches for how to construct adversarial examples. Then I will present a framework, named as adversarial training, for improving robustness of deep networks to defense the adversarial examples, and how to accelerate the training. Moreover,I will show that the introduced adversarial learning framework can be extended as an effective regularization strategy to improve the generalization in semi-supervised learning.
| |
| |
优惠券领取后72小时内有效，10万种最新考研考试考证类电子打印资料任你选。涵盖全国500余所院校考研专业课、200多种职业资格考试、1100多种经典教材，产品类型包含电子书、题库、全套资料以及视频，无论您是考研复习、考证刷题，还是考前冲刺等，不同类型的产品可满足您学习上的不同需求。 ...考试优惠券 本站小编 Free壹佰分学习网 2022-09-19