MATH 440

Math 440: Machine Learning with AI Applications

Prerequisites: STAT 301

Credit Hours: (3)

This course introduces undergraduate students to modern machine learning techniques with a focus on practical artificial intelligence (AI) applications. Topics include supervised learning (classification, decision trees, support vector machines), unsupervised learning (clustering, dimensionality reduction), and an introduction to neural networks. Students explore realworld applications in areas such as image recognition, natural language processing, and recommender systems. The course emphasizes hands-on programming, ethical considerations, and responsible AI practices, including fairness, bias mitigation, and model interpretability.

 

Content

This course provides a practical and accessible introduction to machine learning, tailored for undergraduates interested in data science and AI. It emphasizes algorithms and techniques beyond traditional statistical regression, focusing on classification, clustering, neural networks, and applied AI. Students will program with beginner-friendly libraries to implement models and analyze real-world datasets.
The following topics are covered:

1. Machine Learning Fundamentals such as supervised vs. unsupervised learning, training/validation/test sets, cross-validation, bias–variance tradeoff, and performance metrics (accuracy, precision, recall, F1).
2. Supervised Learning such as logistic regression (review), k-Nearest Neighbors (k-NN), Naive Bayes, Support Vector Machines (SVMs).
3. Decision Trees and Ensembles such as CART, Random Forests, gradient boosting (e.g., XGBoost).
4. Unsupervised Learning such as clustering (k-means, hierarchical clustering) and dimensionality reduction (Principal Component Analysis, PCA).
5. Neural Networks such as perceptrons, feedforward networks, backpropagation, and introduction to deep learning (e.g., convolutional neural networks for images).
6. AI Applications such as image recognition (e.g., MNIST dataset), natural language processing (e.g., sentiment analysis, text classification), recommender systems (collaborative filtering), predictive modeling in health and business contexts.
7. Ethical AI and Interpretability such as fairness, accountability, transparency, mitigating bias, model interpretability, and reproducibility.

 

Detailed Description of Conduct of Course

The course combines interactive lectures, live coding demonstrations, and hands-on programming labs. Lectures introduce core concepts with real-world examples, while labs guide students through implementing models in a programming language at the discretion of the instructor. Weekly discussions address AI’s societal impact and ethical issues. Students will complete applied projects using real datasets, such as building a recommender system or predicting health outcomes.

 

Student Learning Outcomes

Upon completing this course, students will be able to:

1. Understand and apply supervised and unsupervised machine learning algorithms.
2. Implement models in a programming language using open-source libraries and real-world datasets.
3. Evaluate model performance with appropriate metrics and communicate results effectively.
4. Explore AI applications in computer vision, natural language processing, and predictive analytics.
5. Critically assess ethical issues in AI, including bias, fairness, and transparency.

 

Assessment Measures

Assessment of student success will be based on assignments such as exams, homework, projects, final, and other possible measures, the number and weights of which are at the discretion of the instructor.

 

Other Course Information

Basic familiarity with programming is recommended but not required, as introductory coding support will be provided.

 

Review and Approval

February 4, 2026

March 25, 2026