学术交流

Organizers: Shenzhen Research Institute of Big Data (深圳市大数据研究院 in Chinese)                      Shenzhen International Center for Industrial and Applied Mathematics (深圳国际工业与应用数学中心 in Chinese) Speaker: Prof. Weikun Chen Talk title: Cutting planes in mixed integer programming problems Talk abstract: Cutting planes play a crucial role in solving mixed integer programming (MIP) problems. In this talk, we will introduce two cutting planes and their implementations into a MIP solver. The first one is the mixing cut, which is recognized as the most effective cut for solving the MIP formulations o…

10月12日本周三下午15:30-17:10（15:30-16:00茶歇时间）研究院将在道远楼103会议室举行2022年系列研讨会活动的第12次活动，本期将由通用求解器实验室的马丁老师分享主题报告“Ultra-Short-Term Fly Ash Concentration Time Series Forecast: An Integrated Deep Learning Model”。We design an integrated neural network to predict the fly ash concentration at the electrostatic precipitator inlet that is widely used in manufacturing and power plants, to reduce pollutant emissions and energy use. For individual plants, the direct energy-saving and indirect clean air bonus amount to millions of dollars financially, aside from the potential economic credits in the growing carbon mark…

You are cordially invited to the Academic Seminar to be delivered by Dr. Siqi Liu (Online)   Speaker: Dr. Siqi Liu   Topic: Towards Open-environment Visual Perception of Biomedical Signals: from Biometric Security to Medical Diagnostics    Time & Date: 10:00 -11:00, Friday, September 23, 2022 (Beijing time)   Zoom Meeting: https://cuhk-edu-cn.zoom.us/j/97779887050?pwd=RzM3bDNMQ01mWmpURDhiaEljdGVuUT09     Zoom Meeting ID: 977 7988 7050 Password：123456 All of you are warmly welcomed.

9月19日下周一下午15:30-17:10（15:30-16:00茶歇时间）研究院将在道远楼103会议室举行2022年系列研讨会活动的第10次活动，本期将由基础理论与算法研究所的曾奕程老师分享“Random Matrix Theory for Statistics and Machine Learning: Theory and Applications”本主题报告。In this talk, we aim to introduce some basic concepts and methods in random matrix theory (RMT), and deliver intuitions of using RMT tools to statistics and machine learning (ML) by presenting some recent theoretical and applied findings of RMT into ML. Join Zoom Meeting: https://cuhk-edu-cn.zoom.us/j/99284545041?pwd=SitaaThRazAxR2dsTU1OZkRDTjcwQT09 会议号：992 8454 5041 密码：123456

Call for Papers -The Second Doctoral and Postdoctoral Academic Forum of Shenzhen Research Institute of Big Data The Second Doctoral and Postdoctoral Academic Forum will be held in Shenzhen Research Institute of Big Data, on July 30, 2022. This forum provides an opportunity for doctoral students and postdoctoral fellows to discuss and receive feedback on their research from peers and senior practitioners, and help them to make an improvement in innovation ability, paper quality, achievement publishing, etc., to promote their academic progress. Basic information  • Forum Name: The Second Docto…

国际顶级医学图像和计算机辅助介入大会MICCAI2022将于9月在新加坡召开。深圳大数据研究院，香港中文大学（深圳），香港大学，中山大学等多家研究机构将联合深圳市龙岗区人民医院，深圳市龙岗区中心医院举办MICCAI2022多模态腹部分割国际挑战赛（AMOS22），旨在通过开放数据集和挑战赛促进相应医疗分割算法的发展。 挑战赛背景 腹部多器官分割一直是医学图像分析领域最活跃的研究领域之一，其做为一项基础技术，在支持支持疾病诊断，治疗规划等计算机辅助技术发挥着重要作用。 近年来，基于深度学习的方法在该领域中获得了巨大成功，却也暴露出了一个迫切问题: 当前社区缺乏一个大规模的，多样性的，符合真正临床场景的综合基准数据集来开发/评估对应的算法。虽然目前已有几个腹部器官分割数据集，它们的标注器官和标注例子数目却相对有限的， 仍然限制了现代深度模型的力量，也难以对提出的不同方法进行全面和公平的评估。 为了解决上述问题，进一步促进医疗图像分割技术的发展，深圳大数据研究院，香港中文大学（深圳），香港大学，中山大学等机构联合深圳市龙岗区人民医院，深圳市龙岗区中心医院提出了多模态腹部分割数据集（AMOS），一个大规模，多样性的，收集自真实临床场景下的腹部多器官分割基准数据。AMOS 总计提供了500个CT与100个MRI扫描，每个扫描附带了15个腹部器官的体素级标注, 是目前已知最全面的腹…

In recent years, deep learning has achieved great success and many advances in image processing. This workshop aims to discuss the progress, challenges and opportunities of both traditional mathematical model-based and deep learning-based methods in image processing, and seek further integration and development. For more information please visit: http://www.sribd.cn/WorkshopImage/index.html    

“AI安全与隐私”系列论坛第十二期将于4月7日下周四上午10点-11点半举行，此次我们荣幸邀请到了密歇根州立大学汤继良教授分享关于“可信人工智能中的鲁棒性和公平性可以兼得吗？“的主题报告。汤教授是国际知名的学者，在可信人工智能和图神经网络方面做出了颇多开创性的工作。鲁棒性和公平性是深度学习中核心问题之一，汤教授将为大家带来深入的分析。 本次论坛由中科院自动化所梁坚教授担任主持人，由中国图像图形学学会视觉大数据专委会承办，由香港中文大学（深圳）广东省大数据计算基础理论与方法重点实验室和腾讯研究院联合协办，论坛将在Bilibili账号"AI安全与隐私"和腾讯研究院视频号同时直播，欢迎大家届时观看！ 欢迎更多专家莅临本论坛分享您在AI安全与隐私方面的科研成果。