Overview

EG4338/EG6338 Machine Learning

Author
Affiliation

Yike Zhang

St. Mary’s University

gif1

gif2

gif3

Course Summary

Machine Learning is a field at the intersection of computer science, statistics, and data science. This course is designed to provide students from a wide range of backgrounds with a solid foundation in the principles and practices of machine learning. You will learn to define and frame machine learning problems, select and apply suitable algorithms, evaluate results using appropriate metrics, and communicate findings effectively to audiences across disciplines. Throughout this hands-on course, students will engage with important topics such as decision trees, k-means clustering, dimensionality reduction techniques (PCA), neural networks, supervised and unsupervised learning. Programming assignments include hands-on experiments with various classic algorithms. This course is designed to give a undergraduate-level and graduate-level students a thorough understanding in the methodologies and algorithms currently needed by people who do projects/research in machine learning. EG4338 and EG6338 are similar. Undergraduates must register for EG4338.

Prerequisites: None.

Cross Listing Course

EG6338 Machine Learning

Machine Learning is a field at the intersection of computer science, statistics, and data science. This course is designed to provide students from a wide range of backgrounds with a solid foundation in the principles and practices of machine learning. You will learn to define and frame machine learning problems, select and apply suitable algorithms, evaluate results using appropriate metrics, and communicate findings effectively to audiences across disciplines. Throughout this hands-on course, students will engage with important topics such as decision trees, k-means clustering, dimensionality reduction techniques (PCA), neural networks, supervised and unsupervised learning. Programming assignments include hands-on experiments with various classic algorithms. This course is designed to give a undergraduate-level and graduate-level students a thorough understanding in the methodologies and algorithms currently needed by people who do projects/research in machine learning. EG4338 and EG6338 are similar. Graduate students must register for EG6338.

Prerequisites: None.

Course Objectives

After this course, you should be able to …

  • Implementing machine learning algorithms, such as decision trees, k-means clustering, classification and regression.
  • Understanding the principles of dimensionality reduction techniques, such as Principal Component Analysis (PCA).
  • Using probability, statistics, calculus, linear algebra, and optimization in order to develop new machine learning models.
  • Integrating data preprocessing techniques into machine learning workflows.
  • Applying suitable machine learning algorithms to solve complex problems in various domains.
  • Analyzing a machine learning technique to identify several key components:
    • Representation - What kinds of functions or patterns can it represent?
    • Inductive Bias - What assumptions does the algorithm make when it learns from the data?
    • Search Space - How large or complicated is the set of possible solutions?
    • Computation Properties - How fast does the model run and how much memory does it need?
    • Evaluation - How can we measure the performance of the algorithm?
    • Limitations - How well does it typically generalize to new data?
  • Evaluating the performance of machine learning models using appropriate metrics.
  • Understanding the principles of supervised and unsupervised learning.
  • Communicating findings effectively to audiences across disciplines.

What You’ll Learn

The course content includes but not limited to …

  • Introduction to Machine Learning
  • History and Evolution of Machine Learning
  • Machine Learning Applications
  • Decision Trees
  • K-Means Clustering
  • Classification Algorithms
  • Regression Techniques
  • Probability and Statistics in Machine Learning
  • Linear Algebra and Optimization
  • Data Preprocessing Techniques
  • Dimensionality Reduction (PCA)
  • Neural Networks
  • Supervised Learning
  • Unsupervised Learning
  • Reinforcement Learning
  • Machine Learning Tools and Libraries
  • Overfitting and Underfitting
  • Cross-Validation Techniques
  • Model Selection
  • Evaluation Metrics for Machine Learning Models
  • Implement Machine Learning Models
  • Real-world Applications of Machine Learning
  • Ethical Considerations in Machine Learning