1	Course Title:	MACHINE LEARNING
2	Course Code:	ELN5702
3	Type of Course:	Optional
4	Level of Course:	Second Cycle
5	Year of Study:	1
6	Semester:	2
7	ECTS Credits Allocated:	6
8	Theoretical (hour/week):	3
9	Practice (hour/week) :	0
10	Laboratory (hour/week) :	0
11	Prerequisites:
12	Recommended optional programme components:	None
13	Language:	Turkish
14	Mode of Delivery:	Face to face
15	Course Coordinator:	Dr. Ögr. Üyesi GIYASETTİN ÖZCAN
16	Course Lecturers:
17	Contactinformation of the Course Coordinator:	Bilgisayar Müh. Bölüm Binası, 1. kat, oda 107 Tel.:+90 (224) 294 2792 email: gozcan at uludag.edu.tr
18	Website:
19	Objective of the Course:	Feature extraction with statistical techniques from available data. Based on these assessments, to be able to design learning rules. After learning step, to be able to present accurate prediction result.
20	Contribution of the Course to Professional Development

21

Learning Outcomes:

1 Learns to exploit Probability/Statistics rules to attain accurate prediction; 2 Learns SVM Theorem; 3 Learns Bayes Theorem; 4 Learns Ensemble methods; 5 Learns data reduction methods; 6 Learns Expectation maximization; 7 Learns Hidden Markov Models; 8 Learns artificial neural networks and deep learning; 9 Learns to make implementations with R and python;

22	Course Content:

Week	Theoretical	Practical
1	Introduction
2	Bayes Theorem
3	Bayes networks
4	SVM, overfitting
5	Ensemble methods
6	Expectation Maximization, parametric/non parametric methods
7	Data reduction
8	Regression
9	Hidden Markov Models
10	Baum Welsch Algorithm
11	Artificial neural networks
12	Deep learning
13	Python programming and its deep learning interfaces
14	Application development

23	Textbooks, References and/or Other Materials:	1. K. P. Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012. 2. C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
24	Assesment

TERM LEARNING ACTIVITIES	NUMBER	PERCENT
Midterm Exam	1	25
Quiz	0	0
Homeworks, Performances	2	15
Final Exam	1	60
Total	4	100
Contribution of Term (Year) Learning Activities to Success Grade		40
Contribution of Final Exam to Success Grade		60
Total		100
Measurement and Evaluation Techniques Used in the Course
Information

25

ECTS / WORK LOAD TABLE

Activites	NUMBER	TIME [Hour]	Total WorkLoad [Hour]
Theoretical	14	3	42
Practicals/Labs	0	0	0
Self Study and Preparation	0	0	0
Homeworks, Performances	2	19	38
Projects	0	0	0
Field Studies	0	0	0
Midtermexams	1	50	50
Others	0	0	0
Final Exams	1	50	50
Total WorkLoad			180
Total workload/ 30 hr			6
ECTS Credit of the Course			6

26	CONTRIBUTION OF LEARNING OUTCOMES TO PROGRAMME QUALIFICATIONS

LO: Learning Objectives

PQ: Program Qualifications

Contribution Level:

1 Very Low

2 Low

3 Medium

4 High

5 Very High