COURSE UNIT TITLE

: UNSUPERVISED STATISTICAL LEARNING

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
DSM 5008 UNSUPERVISED STATISTICAL LEARNING ELECTIVE 3 0 0 8

Offered By

Graduate School of Natural and Applied Sciences

Level of Course Unit

Second Cycle Programmes (Master's Degree)

Course Coordinator

PROFESSOR DOCTOR NESLIHAN DEMIREL

Offered to

Data Science
Data Science (Non-Thesis-Evening)

Course Objective

To provide students with an in-depth introduction to unsupervised learning methods. We will cover some of the main models and algorithms for clustering. Topics will include Principle Component Aanalysis, k-means and k-medoids clustering, Hierarchical Clustering, Model-Based and Density-Based Clustering. The course will use primarily the R programming language and assumes familiarity with linear algebra, probability.

Learning Outcomes of the Course Unit

1   1. Develop an understanding for what is involved in learning from data
2   2. Reduce the dimension of data
3   3. Apply a variety of clustering methods to data
4   4. Understand how to perform evaluation of clustering algorithms and model selection
5   5. Visualize the clustered data
6   6. Use R programming to apply clustering algorithms

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction to Statistical Learning
2 Principal Components Analysis PCA
3 Principal Components Analysis PCA
4 Clustering Distance Measures-Methods for measuring Distances, What type of distance measures should we choose choose
5 Clustering Distance Measures- Data standardization, Distance matrix computation, Visualizing distance matrices matrices
6 Partitioning Clustering : K-Means Clustering
7 Partitioning Clustering : K- Medoids
8 Assignment Presentations
9 Hierarchical Clustering
10 Hierarchical Clustering-Visualization
11 Model Based Clustering
12 Density Based Clustering (DBSCAN)
13 Cluster Validation
14 Assignment Presentations

Recomended or Required Reading

James G., Witten D., T. Hastie, R. Tibshirani,. An Introduction to Statistical Learning with Applications in R, 2017.
Kassambara A. Practical Guide To Cluster Analysis in R: Unsupervised Machine Learning, 2017.
Alpar R. Uygulamalı Çok değişkenli Istatistiksel Yöntemler, 2017.

Supplementary Book(s):
Materials:
T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning. New York: Springer, 2009.

Planned Learning Activities and Teaching Methods

Lectures, class discussions, homeworks.

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 ASG ASSIGNMENT
2 MTE MIDTERM EXAM
3 FIN FINAL EXAM
4 FCG FINAL COURSE GRADE ASG * 0.30 + MTE * 0.30 + FIN * 0.40
5 RST RESIT
6 FCGR FINAL COURSE GRADE (RESIT) ASG * 0.30 + MTE * 0.30 + RST * 0.40


Further Notes About Assessment Methods

None

Assessment Criteria

Evaluation of homework assignments, presentations, midterm and final exam.

Language of Instruction

Turkish

Course Policies and Rules

Attendance to at least 70% for the lectures is an essential requirement of this course and is the responsibility of the student. It is necessary that attendance to the lecture and homework delivery must be on time. Any unethical behavior that occurs either in presentations or in exams will be dealt with as outlined in school policy.

Contact Details for the Lecturer(s)

Assoc. Prof. Dr. Neslihan DEMIREL
Dokuz Eylul University, Faculty of Sciences, Department of Statistics,
Tinaztepe Campus, 35390, Buca-Izmir
Room number: B-231
e-mail: neslihan.ortabas@deu.edu.tr
Phone: +90.232.3018600

Office Hours

To be anounced

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 14 3 42
Preparations before/after weekly lectures 14 3 42
Preparation for midterm exam 1 30 30
Preparation for final exam 1 30 30
Preparing assignments 2 20 40
Midterm 1 3 3
Final 1 3 3
TOTAL WORKLOAD (hours) 190

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7
LO.15355545
LO.23555
LO.3555555
LO.435555
LO.53555
LO.635555