Loading view.
Week of Events
Learn to Solve Constrained Markov Decision Process Efficiently
Abstract: Many constrained sequential decision-making processes, such as safe AV navigation, wireless network control, caching, cloud computing, etc., can be cast as Constrained Markov Decision Processes (CMDP). Reinforcement Learning (RL) algorithms have been used to learn optimal policies for unknown unconstrained MDP. Extending these RL algorithms to unknown CMDP brings the additional challenge of maximizing the reward and satisfying the constraints. In this talk, I will present algorithms that can learn safe policies effectively. In the second part of the talk, I will demonstrate how the theoretical understanding of the constrained MDP can help us to develop algorithms for practical applications. As an application, I show how to learn to obtain optimal beam directions under time-varying interference-constrained channels for a mobile service robot. Optimal beam selection in mmWave is challenging because of its time-varying nature. We propose a primal-dual Gaussian process bandit with adaptive reinitialization to handle non-stationarity and interference constraints. We demonstrate how our approach learns to adapt effectively to time-varying channel conditions. Co-sponsored by: IEEE North Jersey Section Speaker(s): Dr. Arnob Ghosh, Agenda: Nov 6th, Talk: 7:00 PM - 8:00 PM Discussion Q/A: 8:00 PM - 8:15 PM Room: ECE 202, Bldg: Electrical and Computer Engineering, 154 Summit Street, Newark, New Jersey, United States, 07102
-
IEEE Circuit and System (CAS) Seasonal School on In-Memory Computing (IMC 2024) – First Phase
IEEE Circuit and System (CAS) Seasonal School on In-Memory Computing (IMC 2024) – First Phase
The main goal of this seasonal school is to dive deep into the rapidly developing field of in-memory computing with a focus on Artificial intelligence (AI) and cover its cross-layer design challenges from device to algorithms. The IEEE Seasonal School in Circuits and Systems on In-Memory Computing (IMC 2024) offers talks and tutorials by leading researchers from multiple disciplines and prominent universities and promotes student short presentations to demonstrate new research and results, discuss the potential and challenges of the in-memory accelerators, future research needs, and directions, and shape collaborations. First Talk Title: Developing True Intelligent System: Tools and Case Studies In recent years, we have seen tremendous growth in the AI/ML domain. However, we are still far away from building truly intelligent automated systems. To achieve a true intelligent agent, one should better human decisions and should learn continuously with minimal human intervention. In this talk, we talk about Reinforcement Learning (RL), one key tool to achieving this intelligence. We will discuss the recipe for leveraging RL to create true intelligent systems. As a proof of concept, we discuss two research directions on leveraging RL tools to create intelligent automated agents. Finally, we touch upon some open questions that need to be addressed to realize the dream of true intelligent systems. Second Talk Title: General-Purpose Processing in Memristive Memory Arrays In the last decade, computing systems have faced several challenges that have slowed down their performance improvement substantially. Moreover, we are facing serious challenges and concerns regarding the energy consumption of computing systems. To contain this increasing gap between performance demand and supply alternative paradigms and technologies have been heavily researched. One of the outstanding alternatives is Memory-Centric Computing (MCC). The main idea of MCC is to process data as close as possible to the memory. This reduces the delay and energy overhead associated with loading data for processing and sending it back to the memory for storing the results. MCC can be performed using any memory technology. Among various memory technologies, memristors stand out as one of the best candidates. They are non-volatile, fast, extremely compact, and compatible with the widely used Complementary Metal-Oxide Semiconductor (CMOS) technology. These properties give them an edge in terms of energy efficiency, speed-up gains, price, and their potential share in the future market, respectively. In this talk, we focus on computation inside the memory array and using stateful logics. Processing data inside the array leads to the minimum data travel distance possible, which maximized the associated benefits. We present an overview of some the computational units that we have proposed, such as adders, multipliers, sorting systems, and filters, some of which are combine MCC with other emerging computing paradigms such as stochastic and approximate computing. Co-sponsored by: IEEE North Jersey Section Speaker(s): Dr. Arnob Ghosh, Dr. Nima Taherinejad Agenda: Event Time: 11:00 AM to 1:30 PM 11:00-11:25 AM Registration and Networking 11:25-11:30 AM Opening Remarks by Dr. Shaahin Angizi, Vice-Chair, IEEE CAS/ED Chapter 11:30 AM - 12:00 PM Talk I: Dr. Arnob Ghosh (New Jersey Institute of Technology) Title: Developing True Intelligent System: Tools and Case Studies 12:00-12:45 PM Talk II: Dr. Nima Taherinejad (Heidelberg University, Germany) Title: General-Purpose Processing in Memristive Memory Arrays 12:45 PM - 1:00 PM Networking and Discussion 1:00 PM - 1:30 PM Lunch & Concluding Remarks by Dr. Shaahin Angizi, Vice-Chair, IEEE CAS/ED Chapter Location: CKB 402, New Jersey Institute of Technology, Newark, NJ, USA Online on Zoom, Link: https://njit-edu.zoom.us/j/99695576739 All Welcome: There is no fee/charge for attending IEEE technical seminar. You don't have to be an IEEE Member to attend. Refreshments are free for all attendees. Please invite your friends and colleagues to take advantage of this Invited Distinguished Lecture. Room: ECEC 100, Bldg: ECEC Building, 154 Summit Street, Newark, NJ 07102, NJIT, Newark, New Jersey, United States, 07102
-
A Characterization of All Passivizing Input-Output Transformations of a Passive-Short System
A Characterization of All Passivizing Input-Output Transformations of a Passive-Short System
Passivity theory is one of the cornerstones of control theory providing a systematic way to study the stability of interconnected systems. In practice, many systems are not passive, and must be passivized in order to be included in the framework of passivity theory. Input-output (loop) transformations are the most general tool for passivizing systems. In this paper, we propose a characterization of all possible input-output transformations that map a system with given shortage of passivity to a system with prescribed excess of passivity. We do so by using the connection between passivity theory and cones for SISO systems, and using the S-lemma for MIMO systems. We also present several possible applications of our results, including simultaneous passivation of multiple systems or with respect to multiple equilibria, as well as optimization problems such as $\mathcal{L}_2$-gain minimization. Speaker(s): Daniel Zelazo Agenda: - Talk by Daniel Zelazo at 11:00 am - Lunch box after the talk at 12:00 pm - You don't have to be an IEEE member to attend this meeting. Room: 202, Bldg: ECE, 141 Warren St, New Jersey Institute of Technology, Newark, New Jersey, United States, 07103
-
Worldwide standardization activities of AI
Worldwide standardization activities of AI
In this webinar, we will discuss the newly released ISO standard, ISO/IEC 42001: Artificial Intelligence Management System and its impact on the governance of AI. We will go over the context of the standard, it’s objectives, and the new framework it sets to help organizations build a responsible AI practice, develop an ethical practice, and build a long-term AI strategy. We will also address implications of the EU AI Act on U.S technology companies, and the impact of the EU Act on the issue of conformity assessment and standardization. Finally, we will discuss linkages between 42001 and the NIST Risk Management Framework, and go over the state of federal and local government AI regulations in the U.S Co-sponsored by: Ali Daneshmand Speaker(s): Sid Ahmed, Agenda: Virtual: https://events.vtools.ieee.org/m/428548
-
Women in ECE: Beyond Academics
Women in ECE: Beyond Academics
[] Speaker(s): Chitra Agenda: 4:00- Meet and Greet 4:10- Introduction by Ratna Raj WECE Advisor 4:15- Presentation by guest speaker: Chitra Venkatraman 5:00-5:30 Networking Room: 115, Bldg: ECEC, 323 Martin Luther King Drive, Newark, New Jersey, United States, 07039
-
IEEE North Jersey Section EXCOM – Meeting 6:30 PM
IEEE North Jersey Section EXCOM – Meeting 6:30 PM
The IEEE North Jersey Section's Executive Committee (EXCOM) monthly meeting will be held hybridly. The EXCOM meeting starts at 6:30 pm EST and typically ends at 8:30 pm. The meeting is meant to discuss and coordinate the activities of the Section and its Chapters and Groups, as well as new initiatives. Everyone is welcome to attend this meeting. Please register in advance for this meeting using vTools (Please make a note if you join the meeting remotely) You can change/cancel the registration if your plans change. For more information, please contact our IEEE North Jersey Section Chair Hong Zhao ([email protected]) , or Secretary, Adriaan van Wijngaarden, ([email protected]). Location: New Jersey Institute of Technology To join remotely by the following Zoom link: https://fdu.zoom.us/j/99736508515 Meeting ID: 997 3650 8515 Note: If you are unable to join the meeting, please send your chapter activity report to the section chair at [email protected] Agenda: 06:30 pm - 06:45 pm Networking 06:45 pm - 08:30 pm IEEE North Jersey Section Executive Committee Meeting The meeting agenda typically includes news related to the IEEE and the IEEE North Jersey Section, Secretary and Treasurer reports, Chapter and Affinity Group reports, Committee reports, and reports by various Chairs and Representatives, Committee Chairs, and planning, and new initiatives. Room: ECE 202, Bldg: Electrical and Computer Engineering (ECE) Building, University Heights, Newark, New Jersey, United States, 07102, Virtual: https://events.vtools.ieee.org/m/441739
-
Distinguished Lecture (Virtual) – Civilized Collaboration: Ethical architectures for enforcing legal requirements and mediating social norms in Human-robot Interaction
Distinguished Lecture (Virtual) – Civilized Collaboration: Ethical architectures for enforcing legal requirements and mediating social norms in Human-robot Interaction
Distinguished Lecture (Virtual) - Civilized Collaboration: Ethical architectures for enforcing legal requirements and mediating social norms in Human-robot Interaction Prof. Ronald C. Arkin, Georgia Tech, IEEE Fellow Abstract: The ways in which we treat each other, typically underpinned by an ethical theory, serve as a foundation for civilized activity. Bounds and requirements are established for normal and acceptable interactions between humans. If we are to create robotic systems to reside among us, they must also adhere to a set of related values that humans operate under. This talk first describes the importance of such conventions in human-robot interaction, then outlines a way forward including the difficult research questions remaining to be confronted in ethical human robot interaction (HRI). In particular, examples involving architectures using ethical governors, moral emotions, responsibility advisors and theories of mind are described in two quite different contexts: warfare and the maintenance of human dignity in healthcare. Even the role of deception must be considered as an important adjunct to HRI, as it may yield more effective intentional and autonomous social robots if properly deployed. Finally, we can consider how robots may eventually be able to engineer more socially just human beings via nudging and the ethical questions associated with using such devices. Prof. Ronald C. Arkin is Professor Emeritus with the College of Computing at Georgia TechProf. Arkin was named a Distinguished Lecturer for the IEEE Society on Social Implications of Technology in 2012 and a Distinguished Visitor for the IEEE Computer Society in 2023. He was elected a Fellow of the IEEE in 2003. Co-sponsored by: New York Section and Region 1 & Region 2 Computer Society Speaker(s): Prof. Arkin , Agenda: - Event Agenda - Event Agenda: 6:00 PM Welcome Remark – IEEE NY Section 6:10 ~7:10 PM (Presentation- Prof. Ronald C. Arkin, Georgia Tech, IEEE Fellow, Civilized Collaboration) 7:10 PM Q/A The event is free to attend. ALL ARE WELCOME Virtual: https://events.vtools.ieee.org/m/434465