This connection of springs is a new type of material that can change shape and learn new properties. A new type of material can learn and improve its ability to deal with unexpected forces thanks to a unique lattice structure with connections of variable stiffness, as described in a new paper by my colleagues and me. Architected materials – like this 3D lattice – get their properties not from what they are made out of, but from their structure. The new material is a type of architected material, which gets its properties mainly from the geometry and specific traits of its design rather than what it is made out of. Take hook-and-loop fabric closures like Velcro, for example.

A mechanical neural network composed of beams, motors and sensors can learn to carry out several different tasks, just like its software equivalent, and could lead to aircraft wings that morph during flight to maintain efficiency or minimise turbulence. The basis of modern AI research is the artificial neural network (ANN), which mimics the structure of the human brain by creating large grids of artificial neurons connected by synapses. Just as the human brain learns new behaviours by strengthening synaptic connections, ANNs learn by adjusting the digital values stored to represent them. Ryan Lee at the University of California, Los Angeles, and his colleagues have borrowed that concept to create a mechanical neural network in which the strength of connections between neurons is replaced by beams of variable stiffness. Instead of processing digital data, the mechanical neural network processes forces applied to it, twisting and morphing its shape depending on the stiffness of its beams.

In this paper the Mechanical Neural Network(MNN) is introduced, a physical implementation of a multilayer perceptron(MLP) with ReLU activation functions, two input neurons, four hidden neurons and two output neurons. This physical model of a MLP is used in education to give a hands on experience and allow students to experience the effect of changing the parameters of the network on the output. Neurons are small wooden levers which are connected by threads. Students can adapt the weights between the neurons by moving the clamps connecting a neuron via a thread to the next. The MNN can model real valued functions and logical operators including XOR.