Machine Learning Foundations and Applications

This unit develops core machine learning concepts, enabling students to connect probabilistic reasoning, neural network principles, and accelerator hardware (GPUs, DLPs) to practical AI systems. Students will prepare and evaluate data, explore natural language and human-centered interfaces, and examine applied AI use cases in robotics, drones, industrial environments, and space to inform future model development and deployment.

Learning Objectives

• Analyze the roles of GPU and deep learning processor (DLP) hardware in accelerating machine learning workloads and recommend appropriate processors for given AI tasks
• Apply probability concepts and basic neural network principles to design, simulate, or evaluate simple supervised learning workflows
• Demonstrate data preparation techniques, including cleaning, labeling, and augmentation, to create quality datasets suitable for training and validating models
• Evaluate diverse AI applications — including natural language interfaces, robotics, drones, industrial automation, and space systems — for technical feasibility, human-centered concerns, and potential workforce impacts