Akademik Dersler - Tanıtım


Code - Course Title	EEM511 - Introduction to Machine Learning
Course Type	Required Courses
Language of Instruction	İngilizce
Laboratory + Practice	3+0
ECTS	7.5
Course Instructor(s)	DOÇENT DOKTOR EMİN GERMEN
Mode of Delivery	Mode of delivery of this course is face-to-face instruction.
Prerequisites	Linear algebra, computer programming, statistics
Courses Recomended	BİL 200, MAT 251, İST 244
Required or Recommended Resources	Machine Learning An Algorithmic Perspective, Stephen Marsland, 2’nd Ed, • Neural Networks: A Comprehensive Foundation, Simon Haykin, Papers in current researchs
Recommended Reading List	Vary each year.
Assessment methods and criteria	1 Midterm Exam + 1 Final Exam + 1 Project and Homeworks. The project requires a survey or implementation about a proposed problem.
Work Placement	Not applicable
Sustainability Development Goals

Weeks	Topics
Week - 1	Introduction to Learning Paradigm, Linear Regressin and examples
Week - 2	Polynomial Regression and Statistical Regression, Classification basics
Week - 3	Basic Neuron, Perceptron ve regresional relation. Maximum Likelihood, Gradient descent
Week - 4	Multi Layer Networks, Back Propagation Algorithm
Week - 5	Regularization, Bias/Variance tradeoff, validation, basics, training evaluation metrics
Week - 6	Classification, Naive Bayes
Week - 7	Midterm
Week - 8	Unsupervied Learning, Clustering, K Means Algorithm
Week - 9	Kohonen Self Organizing Map
Week - 10	Feature Extraction, Dimensionality Reduction, Lineer Discriminant Analysis
Week - 11	Dimensionality Reduction, Principal Component Analysis
Week - 12	Random Forest Support Vector Machines
Week - 13	Real World Problems
Week - 14	Student project presentations

Assessment Method and Passing Requirements
	Quamtity	Percentage (%)
1.Midterm Exam	1	30
Homework	1	30
Final Exam	1	40
Toplam (%)		100