| |
Mar 24, 2026
|
|
|
|
|
AAIT 212 - Machine Learning
PREREQUISITES: AAIT 110 - Artificial Intelligence Essentials and SDEV 120 - Computing Logic
CREDIT HOURS MIN: 3
LECTURE HOURS MIN: 3
TOTAL CONTACT HOURS MIN: 48
This course introduces key methodologies in machine learning (ML), emphasizing how each technique aligns with real-world problem domains and use cases. Students will explore how machine learning differs from traditional heuristic approaches to Artificial Intelligence (AI) and examine core paradigms such as classification, regression, clustering, and reinforcement learning. Throughout the course, attention is given to the human and ethical dimensions of data collection, transformation, and model training, ensuring students understand both the technical and responsible practice of machine learning.
MAJOR COURSE LEARNING OBJECTIVES: Upon successful completion of this course, the student will be expected to:
- Identify standard ML algorithms such as classification, regression, clustering, and reinforcement learning.
- Determine appropriate applications for real-world use cases for ML.
- Perform foundational mathematical operations used in ML algorithms: vector operations, feature scaling, and summation notation.
- Apply appropriate input encoding techniques for categorical and numeric data types.
- Interpret code implementations of core supervised and unsupervised ML algorithms.
- Implement the steps of the model training workflow.
- Articulate effective mitigation strategies that minimize sources of bias that arise throughout the training process.
- Interpret metrics to evaluate the accuracy and effectiveness of ML models.
COURSE CONTENT: Topical areas of study include -
- Key ML Paradigms (Supervised, Unsupervised, and Reinforcement Learning)
- Applied ML Use Cases and Problem Domains
- Mathematical Foundations for ML (Vectors, Dot Products, Distance Measures, and Feature Scaling)
- Data Preparation and Encoding Techniques (Categorical and Numeric)
- The ML Workflow (Data Splitting, Training, Validation, and Hyperparameter Tuning)
- Model Evaluation, Metrics, Training, and Performance Interpretation
- Algorithm Implementation and Code Interpretation
- Ethical Considerations and Bias Mitigation in ML
- Introduction to Neural Networks and Emerging ML Architectures
|
|
