Fig. 4: Machine learning framework for inverse design.
From: Machine learning assisted design of shape-programmable 3D kirigami metamaterials
a Schematic of the tandem network architecture employed for the inverse design. The inverse network (i-NN) takes in the desired deformed configuration (\(\theta _{1 - 2},\psi _{1 - 2}^{1 - 2}\)) and predicts a set of geometric features (\(a_{1 - 4}^ \ast\)). The i-NN predicted geometric features (\(a_{1 - 4}^ \ast\)) are fed to the pretrained f-NN to reconstruct the angles of the deformed configuration (\(\theta _{1 - 2}^ \ast\), \(\psi _{1 - 2}^{ \ast 1 - 2}\)) and thereafter validate the predictions of the i-NN. b–e i-NN predicted a1−4 vs true a1−4. f–i f-NN reconstructed \(\psi _{1 - 2}^{1 - 2}\) vs desired \(\psi _{1 - 2}^{1 - 2}\). The corresponding coefficient of determination (R2) are specified on the respective plots.
