INT-2260 Introduction to Machine Learning in R

In this course, students develop an understanding of what machine learning is and how it is different from artificial intelligence. Students examine various types of learning, such as supervised and unsupervised, through analyzing learning algorithms, such as linear and logistic regression, nearest neighbor, decision trees, and the underlying assumptions that drive modeling decisions. Students are introduced to programming in R and learn how knowledge and products can be extracted from large data sets through algorithm selection, model performance assessment, and the manipulation of parameters and hyperparameters. Additionally, students learn about regression algorithms, one- and multi-class classifications, and how ensemble learning can improve predictive performance. Furthermore, challenges such as handling imbalanced datasets, combining models, and optimizing algorithmic efficiency through regularization, clustering, and dimensionality reduction are studied. Lastly, students are introduced to neural networks and deep learning and acquire basic knowledge of neural networks, deep learning, training techniques, and  transfer learning.

Prerequisite(s): INT-1111 .

Course Outcomes

1. Explain machine learning.
2. Compare and contrast different types of machine learning (supervised, semi-supervised, unsupervised and reinforcement).
3. Examine the assumptions that underlie modeling decisions in machine learning.
4. Discuss algorithm selection techniques to choose the most suitable machine learning methods for specific tasks.
5. Extract knowledge and valuable products from large datasets to explain appropriate algorithms.
6. Explain the principle of neural networks in machine learning.