Loading Events

Sequence Learning and Time Series Analysis with Quantum Recurrent Models

Webinar Speaker:

Antonello Rosato

Affiliation: 

Sapienza University of Rome, Italy

About the Webinar

Quantum Machine Learning is gaining increasing attention as a tool for processing the complex and large-scale data produced in Earth Observation. Among the available approaches, Quantum Reservoir Computing and quantum recurrent models show particular promise for capturing temporal patterns and sequential dynamics. The seminar will introduce the basic principles of reservoir computing in both classical and quantum settings, highlighting recent contributions such as quantum dropout, resource-efficient architectures, and novel recurrent models. Examples from forecasting tasks and time-constrained sequence analysis will be discussed, showing how quantum-based methods can complement or improve upon established classical solutions. The presentation will conclude with a perspective on scalability, interpretability, and the challenges that need to be addressed to move towards practical applications of Quantum AI in Earth Science.

About the Speaker

Antonello Rosato was born in 1990. He received his Telecommunication Engineering degree (M.Sc.) with Honors from the University of Rome “La Sapienza”, Italy, in 2015. In 2018, he received the Ph.D. degree in Information and Communications Technologies from the same university. He is currently a Research Fellow at the Dept. of Information Engineering, Electronics and Telecommunications (DIET), University of Rome “La Sapienza”. His research interests include machine learning techniques for prediction of complex behaviors, neural and fuzzy-neural models and systems, distributed clustering algorithms, randomized neural networks performance. His current activities are in the field hyperdimensional computing, quantum computing and applied deep learning for practical implementation in the energy and biomedical domains.

Recorded Webinar

Looking for an older Event? See our Past Events. Events prior to April 2024 can be found in our Events Archive.