Quantum Machine Learning in the NISQ Era: Challenges, Methods, and Applications
27 February 2025
02:45 PM - 03:30 PM
Abstract
This talk provides an overview of the key challenges confronting Quantum Machine Learning (QML) in the NISQ era and presents a structured methodology to address them, including design space exploration and optimization or large QML circuits on limited-qubit NISQ devices. From a trainability standpoint, challenges such as barren plateaus pose significant barriers to the scalability and robustness of QML models. Advanced techniques inspired by classical machine learning, including efficient parameter initialization, integration of residual connections, and systematic design space exploration for accurate, efficient, and robust QML models, have enhanced the trainability and performance of QML architectures. Furthermore, when working with sensitive data, safeguarding privacy is critical. Quantum Federated Learning (QFL) emerges as a robust solution, enabling secure, privacy-preserving learning across distributed systems while achieving high accuracy through collaborative approaches. By addressing these challenges, QML and QFL offer transformative solutions for complex problem-solving and optimized real-time decision-making, underscoring their critical role in advancing quantum technologies across critical domains such as finance, climate modeling, path planning, and different fields.
Dr. Muhammad Shafique
Professor of Electrical and Computer Engineering
NYU Abu Dhabi, Center for Quantum and Topological Systems.
Bio
BiographyRequired to answer. Multi Line Text.
Muhammad Shafique received his Ph.D. degree in Computer Science from the Karlsruhe Institute of Technology (KIT), Germany, in 2011. Afterwards, he established and led a highly recognized research group at KIT for several years as well as conducted impactful collaborative R&D activities across the globe. Before KIT, he was with Streaming Networks Pvt. Ltd. where he was involved in research and development of video coding systems several years. In Oct.2016, he joined the Institute of Computer Engineering at the Faculty of Informatics, Technische Universität Wien (TU Wien), Vienna, Austria as a Full Professor of Computer Architecture and Robust, Energy-Efficient Technologies. Since Sep.2020, Dr. Shafique is with the New York University (NYU), where he is currently a Full Professor and the director of eBRAIN Lab at the NYU-Abu Dhabi in UAE, and a Global Network Professor at the Tandon School of Engineering, NYU-New York City in USA. He is also a Co-PI/Investigator in multiple NYUAD Centers, including Center of Artificial Intelligence and Robotics (CAIR), Center of Cyber Security (CCS), Center for InTeractIng urban nEtworkS (CITIES), and Center for Quantum and Topological Systems (CQTS). His research interests are in AI & machine learning hardware and system-level design, brain-inspired computing, EdgeAI, tinyML, machine learning security and privacy, quantum machine learning, cognitive autonomous systems, wearable healthcare, AI for healthcare/medical imaging, energy-efficient systems, robust computing, hardware security, emerging technologies, electronic design automation, FPGAs, MPSoCs, embedded systems, and quantum computing. His research has a special focus on cross-layer analysis, modeling, design, and optimization of computing and memory systems.