For more than half a century, materials scientists have struggled with how to simulate the complexity of polymer materials.

A surprisingly easy way to multiply an AI model’s profit is to drive decisions via expected value instead of predictive scores. Here's how, illustrated with fraud detection.

For AI models, there are currently no safety rules that govern the path of actions, which can leads to unanticipated consequences.

Abstract: Path tracking is a core technology for autonomous vehicles. Model predictive control (MPC) is well recognized as one of the promising approaches in this field. This article presents an ...

Abstract: This paper presents a novel approach to practical nonlinear model predictive control (PNMPC) using Kolmogorov–Arnold networks (KANs) as prediction models. KANs are based on the ...