05 October. 2021 | 10:00 | (hybrid presentation, on Zoom and CYENS conference room)
Complex systems, both living and artificial, can often be represented as large and dynamic graphs. Network science is a discipline that investigates the topology and dynamics of such graphs aiming to understand the architecture, function and evolution of the underlying systems.
This presentation will discuss how our group has utilized network science in three seemingly different areas with common architectural constraints and objectives:
- The hourglass organization of evolving hierarchical dependencies,
- Multi-sensory integration in the mammalian brain,
- The design of sparse deep neural networks that can learn fast and generalize well.
The talk is designed for a general CS/EE audience with no prior background in network science, neuroscience or deep learning.
Short Bio: Dr. Constantine Dovrolis is a Professor at the School of Computer Science at the Georgia Institute of Technology (Georgia Tech). He is a graduate of the Technical University of Crete (Engr.Dipl. 1995), University of Rochester (M.S. 1996), and University of Wisconsin-Madison (Ph.D. 2000). His research combines Network Science, Data Mining and Machine Learning with applications in climate science, biology, neuroscience, sociology and machine learning. More recently, his group has been focusing on neuro-inspired architectures for machine learning based on what is currently known about the structure of brain networks.
Join Zoom Meeting
Meeting ID: 886 9774 8635