成电讲堂

　　8月20日，IEEE Fellow、IAPR Fellow、北京大学智能学院副院长林宙辰教授做客人力资源部教师发展中心主办的“名师讲堂”，围绕“Optimization Induced Equilibrium Networks: An Explicit Optimization Perspective for Understanding Equilibrium Models”的主题开展精彩报告。讲座由信息与通信工程学院李纯明教授主持。信通、计算机、数学等学院相关专业师生参与了讲座。

　　林宙辰教授谈到，为了揭示深度神经网络 (DNN) 背后的奥秘，优化可能会提供一个很好的视角。已有一些线索表明DNN与优化问题之间存在很强的联系，例如，在温和的条件下，DNN 的激活函数确实是一个近端算子。林宙辰教授团队相关研究工作致力于为一类特殊的网络——平衡模型，即最近变得越来越有吸引力的由不动点方程定义的神经网络，提供统一的优化诱导解释性。为此，首先将DNN分解为一类新的单元层，它是隐式凸函数的近端算子，同时保持其输出不变。然后可以推导出单元层的平衡模型，将其命名为优化诱导平衡网络（OptEq）。OptEq的平衡点理论上可以与具有明确目标的凸优化问题的解相关联。基于此，可以灵活地将先验属性引入平衡点：1）显式修改潜在的凸问题，从而改变OptEq的架构； 2) 将信息合并到不动点迭代中，保证在不动点集为非单例时选择期望的平衡点。结果表明，即使参数较少，OptEq也优于以前的隐式模型。

　　讲座最后，林宙辰教授与参加讲座的师生就人工智能领域的相关研究成果及未来发展方向、深度学习目前面临的一些问题、如何提高科学素养做高质量研究等话题进行了长达三个小时的深入探讨和交流，报告现场反响热烈。

　　相关链接：

　　Zhouchen Lin received the Ph.D. degree in applied mathematics from Peking University in 2000. He is currently a Professor with the Key Laboratory of Machine Perception (MOE), School of Artificial Intelligence, Peking University. He is a Fellow of the IAPR, the IEEE, and the CSIG. He is also a recepient of The National Science Fund for Distinguished Young Scholars. His research interests include machine learning and numerical optimization. He has published over 260 technical papers and 4 monographs, receiving over 25,000 Google Scholar citations. He has been Area Chairs of ACML, ACCV, CVPR, ICCV, NIPS/NeurIPS, AAAI, IJCAI, ICLR, and ICML for many times. He is currently a Program co-Chair of ICPR 2022 and Senior Area Chairs of ICML 2022, NeurIPS 2022, and CVPR 2023. He was an Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence and currently is an associate editor of the International Journal of Computer Vision and Optimization Methods and Software.