Computer Science Colloquium: Prof. Germain Forestier, Univ. of Haute-Alsace, IRIMAS, France

Deep Learning for Time Series Classification

Abstract:
Deep learning has achieved remarkable success across domains such as image processing, computer vision, speech recognition, and NLP. This talk will focus on recent advances in deep learning for univariate and multivariate time series classification, presenting experimental results from leading architectures in the field. I will discuss key challenges, including reducing model complexity, developing foundational models, data augmentation, knowledge distillation, and transfer learning in the context of time series. Finally, I will showcase applications using time series benchmarks, with examples from satellite image time series analysis and human motion analysis.

Short bio:
Prof. Germain Forestier received his PhD in Computer Science from the University of Strasbourg in 2010, followed by a postdoctoral fellowship at INRIA Rennes / INSERM. He joined the University of Haute-Alsace as an Associate Professor in 2011 and has held a Professorship since 2018. Additionally, he is an Adjunct Associate Professor at Monash University (Australia). His research interests encompass data science, data mining, time series, machine learning, big data, artificial intelligence, and deep learning. More info: https://germain-forestier.info/

Export event as iCal