ABSTRACT
The chapter starts with Supervised models design and apply Model Connectivity Hardware Design as part of the Machine Learning models. Supervised models discussed as part of the chapter includes Decision Trees, Random Forest, Adaptive Boosting, Extreme Gradient Boosting (XGB), Linear Regression Models, and Kalman Filter. Next, each of the Supervised models discussed as part of the chapter analyzed from constrained environment perspective and then goes in depth to optimize the Machine Learning model to be effectively functional in the constrained environment. The constrained environment modeling includes Hardware Connectivity Trade-offs, Connectivity Model Trade-offs, and Hardware Connectivity Trade-offs. By following the procedures and the frameworks described as part of the chapter, the Machine Learning and Embedded Engineers can develop Artificial Intelligence models and analyze holistically to successfully deploy in resource constrained environments.
