Michael Deistler

TL;DR: A machine learning tool that uses density estimators based on deep neural networks— trained using model simulations—to infer data-compatible parameters for a wide range of mechanistic models will help close the gap between data-driven and theory-driven models of neural dynamics.

TL;DR: A machine learning tool which uses deep neural density estimators—trained using model simulations—to carry out Bayesian inference and retrieve the full space of parameters compatible with raw data or selected data features, which will help close the gap between data-driven and theory-driven models of neural dynamics.

TL;DR: A PyTorch-based package that implements SBI algorithms based on neural networks facilitates inference on black-box simulators for practising scientists and engineers by providing a unified interface to state-of-the-art algorithms together with documentation and tutorials.

TL;DR: Simulation-based inference (SBI) as discussed by the authors seeks to identify parameter sets that are compatible with prior knowledge and match empirical observations, but does not seek to recover a single 'best' data-compatible parameter set, but rather to identify all high probability regions of parameter space that explain observed data, and thereby quantify parameter uncertainty.

TL;DR: This work uses a novel machine learning method to identify a range of network models that can generate activity patterns matching experimental data, and finds that neural circuits can consume largely different amounts of energy despite similar circuit activity.