BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20250307T001727Z UID:40D48FFD-DF55-4AEE-96D7-344287273944 DTSTART;TZID=Etc/UTC:20241121T120000 DTEND;TZID=Etc/UTC:20241121T130000 DESCRIPTION:Special Presentation by Dr. Farhad Rezazadeh (CTTC\, Spain)\n\n Hosted by the Future Networks Artificial Intelligence & Machine Learning ( AIML) Working Group\n\nDate/Time: Thursday\, November 21st\, 2024 @ 12:00 UTC\n\nTopic:\n\nToward Trustworthy AI/ML in 6G Networks through Explainab le Reasoning\n\nAbstract:\n\nThis talk emphasizes the importance of trustw orthy Artificial Intelligence (AI) in 6G networks in response to growing g lobal attention on AI governance. Notable initiatives such as the White Ho use's Executive Order on the Safe\, Secure\, and Trustworthy Development a nd Use of AI\, DARPA's Assured Neuro-Symbolic Learning and Reasoning and e Xplainable AI (XAI) programs\, and the European Union's AI Act\, highlight the increasing regulatory focus on AI transparency and responsibility. As 6G networks transition from AI-native to automation-native\, the need for explainability and trustworthiness becomes critical\, especially in missi on-critical and high-stakes applications. Traditional post-hoc explainabil ity methods\, which aim to explain AI decisions after they are made\, are no longer adequate in complex network environments. Instead\, in-hoc expla inability or explanation-guided techniques – where explanations guide th e learning process itself – is emerging as a crucial approach for establ ishing trust in AI systems from the ground up. Indeed\, integrating explan atory mechanisms directly within AI learning models enables transparent de cisions and enhances learning. Furthermore\, incorporating neuro-symbolic approaches\, which combine neural networks with symbolic reasoning\, provi des a robust framework to tackle the increasing complexity of 6G networks. By integrating these approaches\, AI systems can make more explainable\, contextually guided decisions\, boosting trust and performance while mitig ating risks associated with black-box AI models.\n\nSpeaker:\n\nFarhad Rez azadeh received his Ph.D. degree (Excellent Cum Laude) in Signal Theory an d Communications from the Technical University of Catalonia (UPC)\, Barcel ona\, Spain. He is currently a researcher (Sr. Applied AI Engineer) at the Telecommunications Technological Center of Catalonia (CTTC)\, Barcelona\, Spain. He participated in 8 European and National 5G/B5G/6G R&D projects with leading and technical tasks in the areas of Applied AI. His AI innova tion in B5G/6G resource allocation was recognized as a great EU-funded Inn ovation by the European Commission's Innovation Radar. He was awarded the first patent connected to the H2020 5G-SOLUTIONS project. He was a seconde e at NEC Lab Europe and had scientific missions at TUM\, Germany\, TUHH\, Germany\, and UdG\, Spain. He is a Marie Sklodowska-Curie Ph.D. grantee\, winning five different IEEE/IEEE ComSoc grants\, two European Cooperation in Science and Technology grants\, and a Catalan Government Ph.D. Grant. H e is an active member of ACM Professional\, IEEE Young Professionals\, and IEEE Spain - Technical Activities and Standards\, with more than 29 top-t ier journals/conferences and book chapters. He actively serves as Organizi ng\, Chair\, Reviewer\, and TPC member in IEEE and Guest Editor for Elsevi er. He has over 140 verified reviews for peer-reviewed publications. He co ordinates the IEEE Trustworthy Internet of Things (TRUST-IoT) working grou p within the IEEE IoT Community.\n\nCo-sponsored by: Toward Trustworthy AI /ML in 6G Networks through Explainable Reasoning\n\nVirtual: https://event s.vtools.ieee.org/m/443359 LOCATION:Virtual: https://events.vtools.ieee.org/m/443359 ORGANIZER:c.polk@comsoc.org SEQUENCE:20 SUMMARY:Toward Trustworthy AI/ML in 6G Networks through Explainable Reasoni ng URL;VALUE=URI:https://events.vtools.ieee.org/m/443359 X-ALT-DESC:Description: <br /><p class="MsoNormal" style="margin-top: .25in \;"><img src="https://events.vtools.ieee.org/vtools_ui/media/display/2d34f eb1-8071-430e-9b4a-e68de21ad78c"></p>\n<p class="MsoNormal" style="margin- top: 12.0pt\;">Special Presentation by<strong> Dr. Farhad Rezazadeh (CTTC\ , Spain)</strong></p>\n<p class="MsoNormal" style="margin-top: 12.0pt\;">H osted by the Future Networks<strong> Artificial Intelligence &amp\; Machin e Learning (AIML) Working Group</strong></p>\n<p class="MsoNormal" style=" margin-top: 12.0pt\;"><strong><span style="font-size: 14.0pt\; font-family : Copperplate\; mso-fareast-font-family: PMingLiU\; mso-fareast-theme-font : minor-fareast\; mso-bidi-font-family: Arial\; mso-bidi-theme-font: minor -bidi\; mso-ansi-language: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi- language: AR-SA\;">Date/Time</span><span style="font-size: 12.0pt\; font-f amily: 'Calibri'\,sans-serif\; mso-ascii-theme-font: minor-latin\; mso-far east-font-family: PMingLiU\; mso-fareast-theme-font: minor-fareast\; mso-h ansi-theme-font: minor-latin\; mso-bidi-font-family: Arial\; mso-bidi-them e-font: minor-bidi\; mso-ansi-language: EN-US\; mso-fareast-language: ZH-T W\; mso-bidi-language: AR-SA\;">: Thursday\, November 21<sup>st</sup>\, 20 24 @ 12:00 UTC</span></strong></p>\n<p class="MsoNormal" style="margin-top : .25in\;"><strong><u><span style="font-size: 16.0pt\; font-family: Copper plate\;">Topic</span></u></strong><strong><span style="font-size: 16.0pt\; font-family: Copperplate\;">:</span></strong></p>\n<p class="MsoNormal">< strong><span style="font-size: 16.0pt\;">Toward Trustworthy AI/ML in 6G Ne tworks through Explainable Reasoning</span></strong></p>\n<p class="MsoNor mal" style="margin-top: .25in\;"><strong><u><span style="font-size: 16.0pt \; font-family: Copperplate\;">Abstract</span></u></strong><strong><span s tyle="font-size: 16.0pt\; font-family: Copperplate\;">:</span></strong></p >\n<p class="MsoNormal" style="margin-top: 6.0pt\;">This talk emphasizes t he importance of trustworthy Artificial Intelligence (AI) in 6G networks i n response to growing global attention on AI governance. Notable initiativ es such as the White House's Executive Order on the Safe\, Secure\, and Tr ustworthy Development and Use of AI\, DARPA's Assured Neuro-Symbolic Learn ing and Reasoning and eXplainable AI (XAI) programs\, and the European Uni on's AI Act\, highlight the increasing regulatory focus on AI transparency and responsibility. As 6G networks transition from AI-native to automatio n-native\, the need for explainability and trustworthiness becomes critica l\, especially in mission-critical and high-stakes applications. Tradition al post-hoc explainability methods\, which aim to explain AI decisions aft er they are made\, are no longer adequate in complex network environments. Instead\, in-hoc explainability or explanation-guided techniques &ndash\; where explanations guide the learning process itself &ndash\; is emerging as a crucial approach for establishing trust in AI systems from the groun d up. Indeed\, integrating explanatory mechanisms directly within AI learn ing models enables transparent decisions and enhances learning. Furthermor e\, incorporating neuro-symbolic approaches\, which combine neural network s with symbolic reasoning\, provides a robust framework to tackle the incr easing complexity of 6G networks. By integrating these approaches\, AI sys tems can make more explainable\, contextually guided decisions\, boosting trust and performance while mitigating risks associated with black-box AI models.</p>\n<p><strong><span style="font-size: 16.0pt\; font-family: Copp erplate\;"><u>Speaker</u>:</span></strong></p>\n<table style="border-colla pse: collapse\; width: 100%\;" border="1"><colgroup><col style="width: 24. 3015%\;"><col style="width: 75.7635%\;"></colgroup>\n<tbody>\n<tr>\n<td><i mg src="https://events.vtools.ieee.org/vtools_ui/media/display/6afad075-38 cb-4168-8d69-3365b037f43b" width="195" height="290"></td>\n<td>\n<p class= "MsoNormal" style="margin-top: 6.0pt\;"><span style="mso-no-proof: yes\;"> Farhad Rezazadeh received his Ph.D. degree (Excellent Cum Laude) in Signal Theory and Communications from the Technical University of Catalonia (UPC )\, Barcelona\, Spain. He is currently a researcher (Sr. Applied AI Engine er) at the Telecommunications Technological Center of Catalonia (CTTC)\, B arcelona\, Spain. He participated in 8 European and National 5G/B5G/6G R&a mp\;D projects with leading and technical tasks in the areas of Applied AI . His AI innovation in B5G/6G resource allocation was recognized as a grea t EU-funded Innovation by the European Commission's Innovation Radar. He w as awarded the first patent connected to the H2020 5G-SOLUTIONS project. H e was a secondee at NEC Lab Europe and had scientific missions at TUM\, Ge rmany\, TUHH\, Germany\, and UdG\, Spain. He is a Marie Sklodowska-Curie P h.D. grantee\, winning five different IEEE/IEEE ComSoc grants\, two Europe an Cooperation in Science and Technology grants\, and a Catalan Government Ph.D. Grant. He is an active member of ACM Professional\, IEEE Young Prof essionals\, and IEEE Spain - Technical Activities and Standards\, with mor e than 29 top-tier journals/conferences and book chapters. He actively ser ves as Organizing\, Chair\, Reviewer\, and TPC member in IEEE and Guest Ed itor for Elsevier. He has over 140 verified reviews for peer-reviewed publ ications. He coordinates the IEEE Trustworthy Internet of Things (TRUST-Io T) working group within the IEEE IoT Community.</span></p>\n<p class="MsoN ormal" style="margin-top: 6.0pt\;">&nbsp\;</p>\n</td>\n</tr>\n</tbody>\n</ table> END:VEVENT END:VCALENDAR