×

From the Internet hourglass architecture, to the mouse brain, and to deep learning

News / Lectures/Workshops / Upcoming / From the Internet hourglass architecture, to the mouse brain, and to deep learning
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:
  1. The hourglass organization of evolving hierarchical dependencies, 
  2. Multi-sensory integration in the mammalian brain, 
  3. 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
https://us02web.zoom.us/j/88697748635?pwd=Ty9LdThIUFl1dktxOTJVSHRkclNDQT09
Meeting ID: 886 9774 8635
Passcode: 667328

More Events
Work in Progress (WIP) showcase
CYENS is hosting the first Work in Progress (WIP) showcase; an arts & technology focused...
01 November. 2021
Invited talk: Representation learning with trainable COSFIRE...
In order to be effective, traditional pattern recognition methods typically require a careful...
19 October. 2021
From the Internet hourglass architecture, to the mouse brain...
Complex systems, both living and artificial, can often be represented as large and dynamic graphs...
05 October. 2021
Nicosia² Accelerator Program - Info Session
Join the Info session to find out more about the accelerator programme and ask questions live! 
15 September. 2021