Metamaterials like sneaker midsoles and car bumpers are engineered to carry load or resist impact, but designing these products to perform as expected can be an error-prone process. Now, Berkeley MSE professor Rayne Zheng and their team have developed an innovative design method that leverages artificial intelligence and additive manufacturing to ensure that optimum functionality and target behaviors are built into these specialized materials. As reported in the latest issue of Nature Communications, researchers used machine learning to inversely design complex mechanical behaviors of a metamaterial and engineering product that can be printed by a desktop 3D printer. The printed materials successfully replicate user-specified material behaviors. This new AI-based design approach could potentially lead to better performing materials, greatly simplify the manufacturing process and enable the development of materials with novel behaviors. The method is also applicable to inverse design other material behaviors beyond mechanical behaviors, including engineered bandgaps, optical and electromagnetic properties. The team created a series of novel metamaterials including robotics, ultrasound and electronics.