Physics-based machine learning for modeling stochastic IP3-dependent calcium dynamics

1 code implementation • 10 Sep 2021 • Oliver K. Ernst, Tom Bartol, Terrence Sejnowski, Eric Mjolsness

We present a machine learning method for model reduction which incorporates domain-specific physics through candidate functions.

BIG-bench Machine Learning

Deep Learning Moment Closure Approximations using Dynamic Boltzmann Distributions

1 code implementation • 28 May 2019 • Oliver K. Ernst, Tom Bartol, Terrence Sejnowski, Eric Mjolsness

Moment closure methods are used to approximate a subset of low order moments by terminating the hierarchy at some order and replacing higher order terms with functions of lower order ones.

Learning Dynamic Boltzmann Distributions as Reduced Models of Spatial Chemical Kinetics

1 code implementation • 2 Mar 2018 • Oliver K. Ernst, Thomas Bartol, Terrence Sejnowski, Eric Mjolsness

Finding reduced models of spatially-distributed chemical reaction networks requires an estimation of which effective dynamics are relevant.

Biological Physics Statistical Mechanics