Pruning deep neural networks generates a sparse, bio-inspired nonlinear controller for insect flight

1 code implementation • 5 Jan 2022 • Olivia Zahn, Jorge Bustamante Jr., Callin Switzer, Thomas Daniel, J. Nathan Kutz

This bio-inspired approach allows us to leverage network pruning to optimally sparsify a DNN architecture in order to perform flight tasks with as few neural connections as possible, however, there are limits to sparsification.

Model Predictive Control Network Pruning