BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Shanghai BEGIN:STANDARD DTSTART:19910915T010000 TZOFFSETFROM:+0900 TZOFFSETTO:+0800 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20261012T134829Z UID:C4285627-4D90-49D6-BC0E-A7B7CBDAF484 DTSTART;TZID=Asia/Shanghai:20261012T150000 DTEND;TZID=Asia/Shanghai:20261012T170000 DESCRIPTION:Dear IEEE CS Guangzhou Chapter Members\,\n\nIEEE CS Guangzhou C hapter will host two academic seminars on the afternoon of October 12\, 20 26 (Monday). All members and interested colleagues are welcome to attend.\ n\nSeminar 1: Graph Structure Learning\n\n- Speaker: Prof. Cesare Alippi ( Politecnico di Milano\, Italy\; Università della Svizzera italiana\, Swit zerland)\n- Time: 15:00 – 16:00\, October 12\, 2026\n- Venue: Room 418\, Engineering Building 2\, Guangdong University of Technology (University T own Campus)\, Guangzhou\n\nAbstract:\nGraph Neural Networks rely on graph structure as a fundamental inductive bias\, yet in many real-world applica tions the underlying relational structure is unknown\, incomplete\, or pot entially inaccurate. Graph Structure Learning (GSL) addresses this challen ge by inferring relational structures directly from data and optimizing th em for the downstream task. This seminar provides an overview of the main approaches to GSL\, focusing on structure initialization\, edge scoring\, graph sparsification\, and loss design. We discuss several strategies for constructing an initial graph\, including Pearson correlation\, Granger ca usality\, pairwise input similarity\, Dirichlet energy minimization\, and graph rewiring. Different edge-scoring approaches are then considered\, ra nging from input-independent parameterizations to input-dependent models b ased on neural networks and attention mechanisms. Particular attention is given to the challenges of learning sparse and discrete graph structures\, including thresholding and Bernoulli sampling\, as well as the gradient-e stimation techniques required for their optimization. Finally\, we discuss how downstream objectives and regularization terms can guide the learned graph toward structures that are both task-relevant and consistent with de sired properties. Overall\, the seminar highlights the potential of GSL as an alternative to predefined graph topologies\, while emphasizing the tra de-offs between expressiveness\, computational efficiency\, and structural constraints.\n\nSeminar 2: Designing Feedback Systems for Rare but Devast ating Events\n\n- Speaker: Prof. Marios M. Polycarpou (University of Cypru s)\n- Time: 16:00 – 17:00\, October 12\, 2026\n- Venue: Room 418\, Engin eering Building 2\, Guangdong University of Technology (University Town Ca mpus)\, Guangzhou\n\nAbstract:\nThe development of AI-enabled cyber-physic al systems with multiple sensor/actuator components and feedback loops has given rise to advanced automation applications\, including energy and pow er\, intelligent transportation\, water systems\, manufacturing\, etc. Tra ditionally\, feedback control has focused on enhancing the tracking and ro bustness performance of the closed-loop system\; however\, as cyber-physic al systems become more complex and interconnected and more interdependent\ , there is a need to refocus our attention not only on performance but als o on the resilience of cyber-physical systems. The goal of this presentati on is to provide insight into the design and analysis of intelligent monit oring methods for AI-enabled cyber-physical systems\, which will ultimatel y lead to more resilient societies.\n\nSpeaker Bios\n\nCesare Alippi is Pr ofessor with the Università della Svizzera italiana (Switzerland) and Pro fessor with the Politecnico di Milano (Italy)\; he is visiting Professor a t the Guangdong University of Technology (China) and Consultant Professor at the Northwestern Polytechnic of Xi'an (China). He has been a visiting r esearcher/professor at UCL (UK)\, MIT (USA)\, ESPCI (F)\, CASIA (RC)\, A*S TAR (SIN)\, U. Kobe (Japan). Alippi is an IEEE Fellow\, ELLIS Fellow\, INN S Fellow and AAIA Fellow\, Past Board of Governors member of the Internati onal Neural Network Society\, Past member of the Administrative Committee of the IEEE Computational Intelligence Society (CIS)\, Past Board of Direc tors member of the European Neural Network Society\, Past Vice-President e ducation of the IEEE Computational Intelligence Society\, Associate Editor of Proceedings of IEEE and other journals\, Past Associate editor of the IEEE Computational Intelligence Magazine\, the IEEE Transactions on Instru mentation and Measurements\, IEEE Transactions on Neural Networks\, IEEE T ransactions on Emerging Topics in Computational Intelligence and member an d chair of many IEEE committees. In 2024 he received the IEEE CIS Enrique Ruspini Meritorious Service Award\, the 2018 IEEE CIS Outstanding Computat ional Intelligence Magazine paper award\, the 2016 Gabor Award from the In ternational Neural Networks Society and the Outstanding Transactions on Ne ural Networks and Learning Systems Paper Award from the IEEE Computational Intelligence Society\; in 2013 the IBM Faculty award\; in 2004 the IEEE I nstrumentation and Measurement Society Young Engineer Award. Current resea rch activity addresses graph-based learning\, adaptation and learning in n on-stationary environments and Intelligence for embedded\, cyber-physical systems and IoT. He holds 8 patents\, has published one monograph book (tr anslated in Chinese)\, 7 edited books and about 250 papers in internationa l journals and conference proceedings.\n\nMarios M. Polycarpou is a Profes sor of Electrical and Computer Engineering and the Chair of the Board of t he KIOS Research and Innovation Center of Excellence at the University of Cyprus. He is also a Founding Member of the Cyprus Academy of Sciences\, L etters\, and Arts\, a Visiting Professor of Imperial College London\, and a Member of Academia Europaea (The Academy of Europe). He served as Foundi ng Chair of the Department of Electrical and Computer Engineering and Foun ding Director of the KIOS Center of Excellence at the University of Cyprus . Prof. Polycarpou is the recipient of the 2023 IEEE Frank Rosenblatt Tech nical Field Award and the 2016 IEEE Neural Networks Pioneer Award for cont ributions to the theory and application of neural networks and learning sy stems in monitoring and control. He is a Fellow of IEEE and IFAC. He serve d as the President of the IEEE Computational Intelligence Society (2012– 2013)\, as the President of the European Control Association (2017–2019) \, and as the Editor-in-Chief of the IEEE Transactions on Neural Networks and Learning Systems (2004–2010). Prof. Polycarpou currently serves on t he Editorial Boards of the Proceedings of the IEEE and the Annual Reviews in Control. His research work has been funded by several agencies and indu stry in Europe and the United States\, including the prestigious European Research Council (ERC) Advanced Grant\, the ERC Synergy Grant and the EU-W idening Teaming program.\n\nRegistration:\nPlease reply to zhwyu@scut.edu. cn or contact the Chapter Secretary if you plan to attend\, so we can esti mate the number of participants.\n\nWe look forward to your participation. \n\nIEEE CS Guangzhou Chapter\nOctober 1\, 2026\n\nRoom 418\, Engineering Building 2\, Guangdong University of Technology\, University Town\, Guangz hou\, Guangdong\, China LOCATION:Room 418\, Engineering Building 2\, Guangdong University of Techno logy\, University Town\, Guangzhou\, Guangdong\, China ORGANIZER:zhwyu@scut.edu.cn SEQUENCE:30 SUMMARY:IEEE CS Guangzhou Chapter Academic Seminar Notice URL;VALUE=URI:https://events.vtools.ieee.org/m/581253 X-ALT-DESC:Description: <br /><p class="p">Dear IEEE CS Guangzhou Chapter M embers\,</p>\n<p class="p">IEEE CS Guangzhou Chapter will host two academi c seminars on the afternoon of October 12\, 2026 (Monday). All members and interested colleagues are welcome to attend.</p>\n<p class="p">Seminar 1: Graph Structure Learning</p>\n<p class="p">- Speaker: Prof. Cesare Alippi (Politecnico di Milano\, Italy\; Universit&agrave\; della Svizzera italia na\, Switzerland)<br>- Time: 15:00 &ndash\; 16:00\, October 12\, 2026<br>- Venue: Room 418\, Engineering Building 2\, Guangdong University of Techno logy (University Town Campus)\, Guangzhou</p>\n<p class="p">Abstract:<br>G raph Neural Networks rely on graph structure as a fundamental inductive bi as\, yet in many real-world applications the underlying relational structu re is unknown\, incomplete\, or potentially inaccurate. Graph Structure Le arning (GSL) addresses this challenge by inferring relational structures d irectly from data and optimizing them for the downstream task. This semina r provides an overview of the main approaches to GSL\, focusing on structu re initialization\, edge scoring\, graph sparsification\, and loss design. We discuss several strategies for constructing an initial graph\, includi ng Pearson correlation\, Granger causality\, pairwise input similarity\, D irichlet energy minimization\, and graph rewiring. Different edge-scoring approaches are then considered\, ranging from input-independent parameteri zations to input-dependent models based on neural networks and attention m echanisms. Particular attention is given to the challenges of learning spa rse and discrete graph structures\, including thresholding and Bernoulli s ampling\, as well as the gradient-estimation techniques required for their optimization. Finally\, we discuss how downstream objectives and regulari zation terms can guide the learned graph toward structures that are both t ask-relevant and consistent with desired properties. Overall\, the seminar highlights the potential of GSL as an alternative to predefined graph top ologies\, while emphasizing the trade-offs between expressiveness\, comput ational efficiency\, and structural constraints.</p>\n<p class="p">Seminar 2: Designing Feedback Systems for Rare but Devastating Events</p>\n<p cla ss="p">- Speaker: Prof. Marios M. Polycarpou (University of Cyprus)<br>- T ime: 16:00 &ndash\; 17:00\, October 12\, 2026<br>- Venue: Room 418\, Engin eering Building 2\, Guangdong University of Technology (University Town Ca mpus)\, Guangzhou</p>\n<p class="p">Abstract:<br>The development of AI-ena bled cyber-physical systems with multiple sensor/actuator components and f eedback loops has given rise to advanced automation applications\, includi ng energy and power\, intelligent transportation\, water systems\, manufac turing\, etc. Traditionally\, feedback control has focused on enhancing th e tracking and robustness performance of the closed-loop system\; however\ , as cyber-physical systems become more complex and interconnected and mor e interdependent\, there is a need to refocus our attention not only on pe rformance but also on the resilience of cyber-physical systems. The goal o f this presentation is to provide insight into the design and analysis of intelligent monitoring methods for AI-enabled cyber-physical systems\, whi ch will ultimately lead to more resilient societies.</p>\n<p class="p">Spe aker Bios</p>\n<p class="p">Cesare Alippi is Professor with the Universit& agrave\; della Svizzera italiana (Switzerland) and Professor with the Poli tecnico di Milano (Italy)\; he is visiting Professor at the Guangdong Univ ersity of Technology (China) and Consultant Professor at the Northwestern Polytechnic of Xi'an (China). He has been a visiting researcher/professor at UCL (UK)\, MIT (USA)\, ESPCI (F)\, CASIA (RC)\, A*STAR (SIN)\, U. Kobe (Japan). Alippi is an IEEE Fellow\, ELLIS Fellow\, INNS Fellow and AAIA Fe llow\, Past Board of Governors member of the International Neural Network Society\, Past member of the Administrative Committee of the IEEE Computat ional Intelligence Society (CIS)\, Past Board of Directors member of the E uropean Neural Network Society\, Past Vice-President education of the IEEE Computational Intelligence Society\, Associate Editor of Proceedings of I EEE and other journals\, Past Associate editor of the IEEE Computational I ntelligence Magazine\, the IEEE Transactions on Instrumentation and Measur ements\, IEEE Transactions on Neural Networks\, IEEE Transactions on Emerg ing Topics in Computational Intelligence and member and chair of many IEEE committees. In 2024 he received the IEEE CIS Enrique Ruspini Meritorious Service Award\, the 2018 IEEE CIS Outstanding Computational Intelligence M agazine paper award\, the 2016 Gabor Award from the International Neural N etworks Society and the Outstanding Transactions on Neural Networks and Le arning Systems Paper Award from the IEEE Computational Intelligence Societ y\; in 2013 the IBM Faculty award\; in 2004 the IEEE Instrumentation and M easurement Society Young Engineer Award. Current research activity address es graph-based learning\, adaptation and learning in non-stationary enviro nments and Intelligence for embedded\, cyber-physical systems and IoT. He holds 8 patents\, has published one monograph book (translated in Chinese) \, 7 edited books and about 250 papers in international journals and confe rence proceedings.</p>\n<p class="p">Marios M. Polycarpou is a Professor o f Electrical and Computer Engineering and the Chair of the Board of the KI OS Research and Innovation Center of Excellence at the University of Cypru s. He is also a Founding Member of the Cyprus Academy of Sciences\, Letter s\, and Arts\, a Visiting Professor of Imperial College London\, and a Mem ber of Academia Europaea (The Academy of Europe). He served as Founding Ch air of the Department of Electrical and Computer Engineering and Founding Director of the KIOS Center of Excellence at the University of Cyprus. Pro f. Polycarpou is the recipient of the 2023 IEEE Frank Rosenblatt Technical Field Award and the 2016 IEEE Neural Networks Pioneer Award for contribut ions to the theory and application of neural networks and learning systems in monitoring and control. He is a Fellow of IEEE and IFAC. He served as the President of the IEEE Computational Intelligence Society (2012&ndash\; 2013)\, as the President of the European Control Association (2017&ndash\; 2019)\, and as the Editor-in-Chief of the IEEE Transactions on Neural Netw orks and Learning Systems (2004&ndash\;2010). Prof. Polycarpou currently s erves on the Editorial Boards of the Proceedings of the IEEE and the Annua l Reviews in Control. His research work has been funded by several agencie s and industry in Europe and the United States\, including the prestigious European Research Council (ERC) Advanced Grant\, the ERC Synergy Grant an d the EU-Widening Teaming program.</p>\n<p class="p">Registration:<br>Plea se reply to zhwyu@scut.edu.cn&nbsp\;or contact the Chapter Secretary if yo u plan to attend\, so we can estimate the number of participants.</p>\n<p class="p">We look forward to your participation.</p>\n<p class="p">IEEE CS Guangzhou Chapter<br>October 1\, 2026</p> END:VEVENT END:VCALENDAR