Dr Konar Debanjan, CASUS—Center for Advanced Systems Understanding Helmholtz-Zentrum Dresden-Rossendorf (HZDR) Görlitz, Germany
Title: Hybrid Classical-Quantum Machine Learning Algorithms for Large Scale Applications
In this talk, I will be discussing primarily on quantum machine learning, quantum optimization, hybrid classical-quantum neural networks with a direct application on computer vision, material science etc. Hybrid classical-quantum spiking and Random neural networks are highly promising candidate for quantum advantage. We propose a novel framework to demonstrate the feasibility of Hybrid Classical-Quantum Neural Networks (HCQNN) employing Variational Quantum Circuit (VQC) in the dressed quantum layer. The HCQNN relies on a hybrid classical-quantum circuit with gate parameters optimized during training. The dressed quantum layer in the suggested DSQ-Net model as a VQC are capable of being trained with thousands of parameters employed in the architecture. The HCQNN model has been experimented on various computer vision datasets using the Penny Lane quantum simulator. Moreover, we are also working on Hybrid Parameterized Quantum Supervised Learning Classifiers. To obviate the data reduction before feeding to the circuit, dense parameterized quantum circuits (VQC) with lesser number trainable parameters have been proposed without compromising the classification accuracy. Recently, we have developed Quantum Kernel Integrated Ridge Regression for the direct applications to material science which will be also the part of our discussion. Finally, I will shed some light in to the future of quantum machine learning and the feasibility of quantum deep learning for large-scale applications.
Keywords: Biomass resource potential, Bioenergy, Biofuels , Biorefineries, Biomass Sustainability Criteria’s, Lignocellulosic biomass. Renewable Energy Systems. Integration Wind-Bioenergy-Solar
Debanjan Konar (Senior Member, IEEE) received the Bachelor of Engineering degree in CSE from the University of Burdwan, India, in 2010, the M.Tech. degree in CSE from the National Institute of Technical Teachers’ Training and Research (NITTTR), Kolkata, India, in 2012, and the Ph.D. degree from the Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India, in 2021. He is currently working as a Postdoctoral Researcher with the Center for Advanced Systems Understanding (CASUS), Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Germany. Prior to this, he has worked as an Assistant Professor with the Department of Computer Science and Engineering, SRM University—AP, Andhra Pradesh, India, and also worked as a Research Assistant Professor with the Sikkim Manipal Institute of Technology, Sikkim, India. His research interests include quantum machine learning, quantum-inspired neural networks, deep learning, and medical image analysis. He has published several articles, including the top-notch journals in computer science, such as IEEE Transactions on Neural Networks and Learning Systems, Applied Soft Computing-Elsevier, IEEE Access, Springer Journals, conference proceedings, book chapters, and edited books of international repute. He is a Senior Member of IEEE, member of ACM and IE, and a reviewer of several esteemed journals and international conferences. Recently, Dr. Konar has won the prestigious Fulbright Postdoctoral fellowship from the field of Computer Science to pursue another postdoc at Purdue University, USA in 2023.
Prof. Eduard Babulac
Department of Computer Science, Mah University, USA.
Prof. Indranil Sengupta, Indian Institute of Technology Kharagpur, India
Prof. Ricardo Armentano, Favaloro University, Buenos Aires, Argentina