Keywords: Machine learning, Variational inference, Data assimilation, Physical biology
Dynamical systems modeling and machine learning for biology. Measurement technology in biology has been advanced drastically in recent decades, and now we can observe molecular/cellular/tissue dynamics at an unprecedented resolution. However, complex data do not always allow us to interpret them clearly. Then, we are using modern machine learning tecnniques to explore meaningful information in the data and to distill it into mathematical models for further analysis.
Living systems as inference machines. Living systems, from bacteria to human, need to sense their environment and act properly in order to survive. This is not easy task due to noisy and limited observations. We are interested in how the living systems perceive and predict the ever-changing external world.
Imaging Platform for Spatio-temporal Information (Seimei-doutai Project)
Grant-in-Aid For Young Scientists (B), "Estimating mechanical properties of moving cell sheets", FY2014-2016