Taming machine learning models of neural dynamics with anatomical and behavioral constraints
Our ability to record large-scale neural and behavioral data has substantially improved in the last decade. However, the inference of quantitative dynamical models remains challenging due to their unconstrained nature. Here, we incorporate constraints from anatomy and physiology to tame machine learning models of neural activity and behavior. I will show that these constraints-based modeling approaches allow us to predictively understand the relationship between neural activity and behavior.
How does the motor cortex achieve generalizable and purposeful movements from the complex, nonlinear musculoskeletal system? I will present a deep reinforcement learning framework for training recurrent neural network controllers that act on anatomically accurate limb models such that they achieve desired movements. We apply this framework to kinematic and neural recordings made in macaques as they perform movements at different speeds. This framework for the control of the musculoskeletal system mimics biologically observed neural strategies and enables hypothesis generation for prediction and analysis of novel movements and neural strategies.
Widefield calcium imaging enable recordings of large-scale neural activity across the mouse dorsal cortex. Here, it is critical to demix the recordings into meaningful spatial and temporal components that can be mapped onto well-defined brain regions. To this end, we developed Localized semi-Nonnegative Matrix Factorization (LocaNMF) to extract and model the activity of different brain regions in individual mice. The decomposition obtained by LocaNMF results in interpretable components which are robust across subjects and experimental conditions. Moreover, modeling behavior across different subjects and in a naturalistic setting remains a significant challenge in the field of behavioral quantification. We develop novel explainable AI methods for modeling continuously varying differences in behavior, which successfully represent distinct features of multi-subject and social behavior in an unsupervised manner. These methods are also successful at uncovering the relationships between recorded neural data and the ensuing behavior. The outcomes of this interdisciplinary research will inform new avenues for clinical applications for the treatment of neurological disorders.
Shreya Saxena is broadly interested in the neural control of complex, coordinated behavior. She is an Assistant Professor at the University of Florida’s Department of Electrical and Computer Engineering. Before this, Shreya was a Swiss National Science Foundation Postdoctoral Fellow at Columbia University’s Zuckerman Mind Brain Behavior Institute in the Center for Theoretical Neuroscience. She did her PhD in the Department of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology studying the closed-loop control of fast movements from a control theory perspective. Shreya received a B.S. in Mechanical Engineering from the Swiss Federal Institute of Technology (EPFL), and an M.S. in Biomedical Engineering from Johns Hopkins University. She is honored to have been selected as a Rising Star in both Electrical Engineering (2019) and Biomedical Engineering (2018).