DESCRIPTION
This lecture will cover recent advances in methodologies to forecast quantities using deep
neural networks with applications to autonomous agents, video streaming and network
traffic forecasting. We first briefly introduce sequence prediction problems introducing
the main architectural choices, such as RNNs, LSTMs and Transformers. Then we will
delve into forecasting of agent motion in different settings, reporting on our recent
research in social trajectory forecasting with the use of memory augmented neural
networks. Finally, we will conclude with recent results on large models for time series
forecasting and their application to network traffic estimation.
DETAILS
Course type: Invited lecture
Duration: 1 -1:30 hours
Level: Postgraduate/PhD
Institution of lecturer: University of Florence, Italy
LECTURER
Prof. Lorenzo Seidenari
Lorenzo Seidenari is an Associate Professor of Computer Engineering at the Department of Information Engineering of the University of Florence. His research interests are focused on Deep Learning and its applications to Computer Vision and Robotics. He’s an ELLIS scholar, and frequently serves as Area Chair for ACM Multimedia (MM), British Machine Vision Conference (BMVC). He’s associate Editor of Multimedia Tools and Applications and Pattern Recognition. He has authored more than 100 conference and journal papers. He was awarded several research grants and lead several technology transfer project with international industrial partners.