Teuvonet employs simplified, patent-pending capabilities running on GPU or FPGA Systems on a Chip (SoCs) to train, test, and execute machine learning models near the IoT/IIoT Edge in real-time. Unlike cloud-edge hybrids, where modeling takes place on the cloud, Teuvonet models are trained and run at the edge of IoT. This obviates the need to transfer and store data on the cloud. The models supported by Teuvonet include function approximation, classification, clustering, anomaly detection, and feature selection. The models are designed to support a variety of applications and industries.