University of Michigan researchers showed how mechanical neural networks—the black lattices of triangles—could be trained to solve problems. Disclaimer: AAAS and EurekAlert! are not ...

Engineering simulations often require significant computational resources and time, which creates barriers for users and can ...

The researchers showed the gradient could be found experimentally using a 3D-printed model of a mechanical neural network.

The U-M team of Shuaifeng Li and Xiaoming Mao devised an algorithm that provides a mathematical framework for how learning works in lattices called mechanical neural networks. "We're seeing that ...

The study was published in Advanced Functional Materials and featured on its cover. The researchers fabricated nanoscale ...