Generative Adversarial Networks (GANs) implement Machine Learning (ML) algorithms that can address competitive resource allocation problems, together with detection and mitigation of anomalous behavior. In this talk, the speaker will discuss their use in next-generation (NextG) communications within the context of cognitive networks to address i) spectrum sharing, ii) detecting anomalies, and iii) mitigating security attacks. GANs have the following advantages. First, they can learn and synthesize field data, which can be costly, time-consuming, and non-repeatable. Second, they enable pre-training classifiers by using semisupervised data. Third, they facilitate increased resolution. Fourth, they enable recovering corrupted bits in the spectrum. The talk will provide basics of GANs, a comparative discussion on different kinds of GANs, performance measures for GANs in computer vision and image processing as well as wireless applications, a number of datasets for wireless applications, performance measures for general classifiers, a survey of the literature on GANs for i)–iii) above, some simulation results, and future research directions. In the spectrum sharing problem, connections to cognitive wireless networks are established. Simulation results show that a particular GAN implementation is better than a convolutional autoencoder for an outlier detection problem in spectrum sensing. Co-sponsored by: Vishnu S. Pendyala, SJSU Speaker(s): Dr. Vishnu S. Pendyala, Prof. Ender Ayanoglu Virtual: https://events.vtools.ieee.org/m/493301

Free Registration (with a Zoom account; you can get one for free if you don't already have it. This requirement is to avoid Zoom bombing. Please sign in using the email address tied to your Zoom account — not necessarily the one you used to register for the event.): https://sjsu.zoom.us/webinar/register/WN_DIDfdbkgRFeEd3JbzURIUQ Synopsis: How are machine learning algorithms able to answer questions from any nook and corner of the World Wide Web? How are trending hashtags from the near infinite microblog posts, unique visitors and other distinct counts in the near infinite website traffic determined? How do blogging websites avoid recommending articles a user has previously read? In general, how can we answer complex queries about enormous data streams without storing them entirely, in real-time? The answer often lies in clever approximation algorithms and data "sketches" that capture essential properties using vastly reduced space. The relentless flow of data in modern systems indeed presents significant challenges. These data streams are often too large to store and too fast to process exhaustively with traditional methods. This talk introduces key sketching and approximation techniques that help generate real-time data insights by processing data streams. --------------------------------------------------------------- By registering for this event, you agree that IEEE and the organizers are not liable to you for any loss, damage, injury, or any incidental, indirect, special, consequential, or economic loss or damage (including loss of opportunity, exemplary or punitive damages). The event will be recorded and will be made available for public viewing. Speaker(s): Dr. Vishnu S. Pendyala Virtual: https://events.vtools.ieee.org/m/482936

IEEE SF/OEB Power & Energy Society (PES) is excited to announce our upcoming PG&E Diablo Canyon Power Plant Site Visit on Thursday August 21, 2025, from 8am to 2pm, with 7:30am arrival! We have a limited number of spots and expect it to fill up fast. Please register on vTools ASAP but only if you believe you can make it. You will need to travel to Avila Beach on August 20th to be there the night before. Site Tour will include a risk management presentation and site visits to turbine deck, control room simulator, Independent Spent Fuel Storage Installation, and marina. Once you have registered, SF PES Chair Wendy Al-Mukdad will send you the PG&E event registration with a lot more information about preparing for your visit, pre-tour safety video, visitor rules & information. PG&E must pre-approve all registered attendees no later than 2 weeks before the event. IEEE SF/OEB PES attendees tentatively are planning to meet for dinner on Wednesday August 20th in Avila Beach. More info to follow. Please contact Wendy at walmukdad@ieee.org with any questions. Avila Beach, California, United States

IEEE SCV WIE AI Summit 2025 In an era where AI technologies are rapidly transforming industries and redefining possibilities, it is crucial to explore both the innovations driving this change and the responsibilities that come with it. Today, we will delve into a diverse array of topics that highlight the multifaceted nature of AI and its profound impact on our lives. Our sessions will cover the latest developments in Large Language Models and Foundation Models, exploring efficient fine-tuning, multilingual adaptation, and the role of LLMs as knowledge bases. We will also examine the evolution of AI agents, focusing on autonomous task completion, multi-agent collaboration, and the integration of external knowledge for robust decision-making. In the realm of Vision and Multimodality, we will explore the integration of text, image, and video understanding, as well as advanced techniques like zero-shot learning and self-supervised learning. Our discussions on MLOps for LLMs will provide insights into best practices for training, deploying, and evaluating large models. We will also address the critical areas of Knowledge-Grounded Reasoning, On-Device Learning, and the ethical dimensions of AI, including bias mitigation, privacy preservation, and the detection of misinformation. Talk tracks are broadly classified but not limited to, 1. Large Language Models (LLMs) & Foundation Models 2. AI Agents 3. Vision & Multimodality 4. MLOps for LLMs 5. Knowledge-Grounded & Reasoning 6. On-Device Learning for LLMs and Multi-Modal AI 7. Ethics, Bias & Fairness Speaker(s): Jagruti Mahante & Shreya Anand, Jesmin Jahan Tithi, Harika Rama Tulasi Karatapu, Pallishree Panigrahi, Rong Wang and Sushma Venkatesh Reddy, Disha Ahuja, Shubhi Asthana Agenda: 3:15-4:00 Registration 4:00-4:10 IEEE SCV WIE Welcome Message 4:15-4:45 Multi-Agentic Synthetic Data Generation for Realistic, Multi-Turn Conversations - By Disha Ahuja, Cisco 4.50-5.20 The LLM Imperative: Secure Your AI Frontier Before It Fractures Your Enterprise - By Jagruti Mahante & Shreya Anand, Workday 5:25-5:55 Designing Data Centers for Next-Gen Language Models - By Jesmin Jahan Tithi, Intel 5:55-6:30 Networking and Refreshments 6:30-6:50 ReAct Prompt Design: Enhancing LLM Reasoning & Tool Use - By Shubhi Asthana, IBM 6:55-7:15 AI Powered SaaS on GCP - By Harika Rama Tulasi Karatapu, Google 7:20-7:40 Designing for Trust: Responsible AI from Data to Deployment - By Pallishree Panigrahi, Amazon 7:45-8:05 The First Enablement of GPU On-Device LLMs on Intel Chromebook Platforms - By Rong Wang and Sushma Venkatesh Reddy, 8:05-8:10 Final Wrap-up Bldg: SC12, Intel, 2200 Mission College Blvd, Santa Clara, California, United States, 95054