从复杂系统到生成式人工智能 | 周一直播·AI by Complexity读书会
导语
主题:从复杂系统到生成式人工智能
主题:从复杂系统到生成式人工智能
分享大纲
-
复杂系统背景介绍
-
复杂系统驱动的机器学习框架
-
生成式人工智能技术原理算法
-
Chen R T Q, Rubanova Y, Bettencourt J, et al. Neural ordinary differential equations. Advances in Neural Information Processing Systems, 2018, 31.
-
Dupont E, Doucet A, Teh Y W. Augmented neural odes. Advances in Neural Information Processing Systems, 2019, 32.
-
Qunxi Zhu, Yao Guo, and Wei Lin [2021], Neural delay differential equations, 9th International Conference on Learning Representations (ICLR 2021).
-
Pathak J, Hunt B, Girvan M, et al. Model-free prediction of large spatiotemporally chaotic systems from data: A reservoir computing approach. Physical Review Letters, 2018, 120(2): 024102.
-
Min Yan, Can Huang, Peter Bienstman, Peter Tino, Wei Lin, and Jie Sun [2024], Emerging opportunities and challenges for the future of reservoir computing, Nature Communications, vol. 15, Art. no. 2056.
-
Xin Li, Qunxi Zhu, Chengli Zhao, Xiaojun Duan, Bolin Zhao, Xue Zhang, Huanfei Ma, Jie Sun, and Wei Lin [2024], Higher-order Granger reservoir computing: Simultaneously achieving scalable complex structures inference and accurate dynamics prediction, Nature Communications, vol. 15, Art. no. 2506.
-
Song Y, Sohl-Dickstein J, Kingma D P, et al. Score-Based Generative Modeling through Stochastic Differential Equations. International Conference on Learning Representations (ICLR 2021).
-
Lipman Y, Chen R T Q, Ben-Hamu H, et al. Flow Matching for Generative Modeling. The Eleventh International Conference on Learning Representations (ICLR 2023).
-
Qunxi Zhu and Wei Lin [2024], Switched flow matching: Eliminating singularities via switching ODEs, 41st International Conference on Machine Learning (ICML 2024).
直播信息
直播信息
时间:2024年8月12日(周一)20:00-22:00
AI By Complexity读书会招募中
大模型、多模态、多智能体层出不穷,各种各样的神经网络变体在AI大舞台各显身手。复杂系统领域对于涌现、层级、鲁棒性、非线性、演化等问题的探索也在持续推进。而优秀的AI系统、创新性的神经网络,往往在一定程度上具备优秀复杂系统的特征。因此,发展中的复杂系统理论方法如何指导未来AI的设计,正在成为备受关注的问题。
集智俱乐部联合加利福尼亚大学圣迭戈分校助理教授尤亦庄、北京师范大学副教授刘宇、北京师范大学系统科学学院在读博士张章、牟牧云和在读硕士杨明哲、清华大学在读博士田洋共同发起「AI By Complexity」读书会,探究如何度量复杂系统的“好坏”?如何理解复杂系统的机制?这些理解是否可以启发我们设计更好的AI模型?在本质上帮助我们设计更好的AI系统。读书会于6月10日开始,每周一晚上20:00-22:00举办。欢迎从事相关领域研究、对AI+Complexity感兴趣的朋友们报名读书会交流!
往期分享:
点击“阅读原文”,报名读书会