Project description
Machine learning-based model for in-depth study of cognition
The introduction of mechanistic models well aligned with experimental data could significantly improve understanding of cellular and network properties underlying cognition, and what leads to pathological conditions. Funded by the Marie Skłodowska-Curie Actions programme, the AutoMIND project proposes to develop a machine learning-based model inference tool capable of identifying parameters of particular spiking neural network models while capturing arbitrary target neural dynamics from human brain recordings. The tool capitalises on recent advances in simulation-based inference techniques, incorporating simultaneous parameter manifold-learning and gradient-based simulations. Moreover it is capable of solving neuroscientific problems via in silico experiments.
Objective
Human cognition depends on complex coordinated dynamics of neural populations, which is shaped by a rich heterogeneity in cellular properties and network connectivity patterns of neural circuits. While cognitive neuroscience leverages macroscopic brain signals to relate neural activity to behavioral states, we currently cannot dissect them for their physiological contributions, hindering mechanistic interpretations of experimental data. One way to systematically study how physiological parameters shape neural dynamics is through mechanistic modeling of spiking neural networks. However, current modeling approaches are not quantitatively constrained by observed electrophysiological data, and often require painstaking and ad-hoc parameter-tuning by hand. Efficient discovery of mechanistic models that are consistent with experimental data would dramatically accelerate our understanding of how cellular and network properties impact cognition, and why it breaks down in pathological states, representing a radical departure from how neural data is analyzed in cognitive neuroscience. To this end, I propose to develop a machine learning-assisted model inference tool—Automated Model Inference from Neural Dynamics (AutoMIND)—that can identify parameters of candidate spiking neural network models that could capture arbitrary target neural dynamics from human brain recordings. AutoMIND extends on recent advances in simulation-based inference techniques, incorporating simultaneous parameter manifold-learning and gradient-based simulations. AutoMIND has broad utility for tackling neuroscientific questions by enabling expedited in-silico experiments. Here, I apply it to multiscale neural data to study how cellular and network properties shape: 1) the emergence of synchronous network oscillations during early neurodevelopment, and 2) the difference in neural dynamics and computation between sensory and association cortices—two questions of fundamental importance to neuroscience.
Fields of science
Keywords
Programme(s)
Funding Scheme
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Coordinator
72074 Tuebingen
Germany