Theory of Multi-Scale Neuronal Networks
About
The focus of this group are mechanisms that shape the dynamics and information processing in biological and artificial neuronal networks. On the side of biological networks, we are interested in the relationship between the structure and dynamics of neural networks to unveil experimentally testable mechanisms of collective phenomena. For artificial neuronal networks, we develop the physics of AI that allows us to understand and quantify generalization properties and learning. Employing and developing statistical physics methods to formulate biological and artificial networks in a unified language, allows us to discover overarching principles of information processing and to detect and quantify qualitative differences.
Research Topics
dynamics of neuronal networks, mechanisms of neuronal information processing, physics of machine learning, transfer and adaptation of methods from statistical physics
research Foci
Dynamic Mechanisms in Neural Networks
- Oscillations
- Statistics of correlations
- Dimensionality
- Chaos
Mechanisms of Neural Information Processing
- Biological and artificial neural networks
- Generalization properties
- Field theory of feedforward and recurrent networks
We employ methods of statistical physics to understand information processing in biological and artificial neuronal networks (physics of AI). Using methods from equilibrium and non-equilibrium and statistical field theory, we study learning in the setting of Bayesian inference to obtain insights into the expressibility and generalization properties of neuronal networks. This mathematical language applies to both, biological and artificial network architectures and allows us to distill common underlying mechanisms and to quantify differences. Collective dynamical properties, such as chaotic dynamics and the closeness to critical points, for example decisively shape learning and generalization in recurrent biological networks and artificial feed forward ones.
Methods Transfer and Adaptation from Theoretical Physics
- Statistical field theory
- Theory of disordered systems
- Methods from Statisitcal Physics (Fokker Planck theory, Edgeworth expansion, etc.)
Members
Collaborations (external)
Tobias Kühn
Alexandre Rene
Stefano Recanatesi
Eric Shea-Brown
Gabriel K. Ocker
Xiaoxuan Jia
Luke Campagnola
Tim Jarsky
Stephanie Seeman
Alexa Riehle
Thomas Brochier
Lukas Deutz
Nicole Voges
Paulina Dabrowska
Michael von Papen
Andrea Cristanti
Funding
Helmholtz networking fund
BMBF
DFG Excellence initiative (ERS RWTH)