Prepare data for basic machine-learning workflows
Computing, Communication & Enterprise · Computer Science & Artificial Intelligence
AI-210Machine Learning Foundations
Introduces supervised and unsupervised learning, model evaluation, features, data quality, bias, and responsible application.
Course outcomes
What students develop
Train and evaluate common models
Identify overfitting, leakage, bias, and distribution shift
Communicate performance and limitations
Course content
Topics and questions
- Regression and classification
- Clustering and dimensionality reduction
- Features and preprocessing
- Validation and metrics
- Bias, fairness, and model limits
Methods & resources
Tools and environments
- Python machine-learning libraries
- Notebook environment
- Versioned datasets
Evaluation
Demonstration of learning
- Model laboratories
- Evaluation memo
- Applied machine-learning project
Program relationships
Where this course fits
Core
Electrical Systems, Sensing & Robotics
Integrates electronics, embedded systems, sensors, controls, robotics, field automation, data acquisition, and engineering design.
Core
Computational Intelligence & Data Systems
Combines computer science, AI, data engineering, research computing, visualization, systems thinking, and responsible application.
Core
Applied AI, Research Computing & Visualization
Advanced computational methods for research, data-intensive inquiry, AI systems, visualization, reproducibility, and decision environments.
Core
Complex Adaptive Systems
Emergence, feedback, adaptation, networks, agent interaction, simulation, resilience, and cross-scale systems reasoning.
Core
Applied Artificial Intelligence
Machine learning, language and multimodal models, retrieval, tools, evaluation, governance, and operational AI systems.
Course inquiry
Connect this course to a program, certificate, or professional objective.
Join the interest list or request a course and pathway conversation.