Quantum Machine Learning (QML): Quantum Architecture Search (QAS)

#AI #ML #quantum #MachineLearning #QML #QAS #VQC #PQC #NISQ #QuantumComputing #QuantumInformation #futurenetworks #ieee #webinar

Special Presentation by Dr. Samuel Yen-Chi Chen (Wells Fargo, USA)

Co-Hosted by the Future Networks AI/ML and QIT working groups

Date/Time: Thursday, 2 October 2025 @ 6 PM EDT

PDH Certificate: while basic attendance is free, this course also offers one (1) Professional Development Hour (PDH) for a nominal fee; please choose the appropriate "Registration Fee" when registering; additional terms and conditions apply.

Topic:

Quantum Machine Learning: Quantum Architecture Search

Abstract:

Quantum Machine Learning (QML) stands at the cutting edge of computational intelligence, integrating quantum computing with classical machine learning to tackle complex problems beyond the reach of conventional methods. This talk will examine how QML harnesses quantum mechanical principles — including superposition, entanglement, and interference — to enable novel learning paradigms. Special emphasis will be placed on variational quantum circuits (VQCs) as a core building block for designing QML models on noisy intermediate-scale quantum (NISQ) hardware. In addition, I will introduce emerging techniques in Quantum Architecture Search (QAS), which automate the discovery and optimization of quantum circuit structures tailored for specific learning tasks. Drawing on our latest research, I will showcase applications where QML and QAS synergistically advance performance across multiple domains. The presentation will conclude by discussing the mutual reinforcement between artificial intelligence and quantum computing, outlining both the opportunities and key challenges that shape the future of QML

Speaker:

Samuel Yen-Chi Chen is a Lead Research Scientist at Wells Fargo, specializing in Quantum Machine Learning (QML), Reinforcement Learning, and Neural Architecture Search. With a Ph.D. in Physics and extensive experience across quantum AI, high-performance computing, and algorithmic design, he has published over 60 papers in IEEE, APS, IOP, and leading AI conferences. Samuel is best known for his work on Quantum Reinforcement Learning (QRL), Quantum Long Short-Term Memory (QLSTM), Quantum Fast Weight Programming, and the Differentiable Quantum Architecture Search (DiffQAS) framework. He has organized multiple workshops and tutorials at IEEE ICASSP, ISCAS, FUZZ, QCE, GLOBECOM,WCNC, ICC, and IJCNN, and continues to push the boundaries of hybrid quantum-classical intelligence. His current research explores self-evolving quantum agents and structure-aware QNN design for time-series learning, quantum reinforcement learning, and communication systems.