DEGREE PROGRAMS  Associate's Degree (Short Cycle)  Bachelor’s Degree (First Cycle)  Master’s Degree (Second Cycle)

Course Description Course Name : Machine Learning Course Code : CENG-509 Course Type : Optional Level of Course : Second Cycle Year of Study : 1 Course Semester : Fall (16 Weeks) ECTS : 6 Name of Lecturer(s) : Asst.Prof.Dr. MUTLU AVCI Learning Outcomes of the Course : Comprehends basic mathematical structures of machine learning Understands supervised learning methods and implement their software Understands unsupervised learning methods and implement their software Determines learning parameters and appropriate machine learning model Designs tests and analyse their results Implements machine learning methods in various application areas Mode of Delivery : Face-to-Face Prerequisites and Co-Prerequisites : None Recommended Optional Programme Components : None Aim(s) of Course : To understand machine learning and statistical pattern recognition methods, implement their software and use as solution to classification, decision and prediction problems. Course Contents : Mathematical structures. introduction to MATLAB environment. Supervised learning methods: learning of single layer and multilayer neural networks, probabilistic methods, Bayesian statistics, decision trees, hidden Markov model, support vector machines. Unsupervised learning methods: clustering, dimensionality reduction and kernel methods. Learning theories: VC theory, bias/ variance tradeoffs, importance of model selection and generalization. Reinforcement learning. Test design and analysis of results: k fold cross validation method. Information of machine learning application areas. Language of Instruction : English Work Place : Classrooms for master students   Course Outline /Schedule (Weekly) Planned Learning Activities Week Subject Student's Preliminary Work Learning Activities and Teaching Methods 1 Mathematical structures for machine learning methods Reading corresponding subjects of textbooks Lecturing and solving example problems 2 Introduction to MATLAB environment, basic functions, creating script and function Homework 1 Slide presentation and applications with MATLAB 3 Differences between supervised and unsupervised learning methods. Single layer and multilayer neural networks, backpropagation method Reading corresponding subjects of textbooks Lecturing 4 Bayesian Decision Theory, Naive Bayes Reading corresponding subjects of textbooks + Homework 2 Lecturing 5 Radial basis function neural networks: generalized regression neural networks, probabilistic neural networks Reading corresponding subjects of textbooks + Homework 3 Lecturing 6 Learning theory: VC dimension, bias/variance tradeoff, model selection Reading corresponding subjects of textbooks + Homework 4 Lecturing 7 Fuzzy logic, decision trees Reading corresponding subjects of textbooks + Homework 5 Lecturing 8 Midterm Exam Examination 9 Unsupervised learning methods, clustering, K means clustering Reading corresponding subjects of textbooks + Homework 6 Lecturing 10 Expectation maximization, Gaussian mixtures Reading corresponding subjects of textbooks + Homework 7 Lecturing 11 Feature selection, principle component analysis, independent component analysis Reading corresponding subjects of textbooks + Homework 8 Lecturing 12 Hidden Markov model Reading corresponding subjects of textbooks + Homework 9 Lecturing 13 Support vector machines Reading corresponding subjects of textbooks + Homework 10 Lecturing 14 Reinforcement learning Reading corresponding subjects of textbooks + Homework 11 Lecturing 15 Test design and analysis of results, k fold cross validation method Reading corresponding subjects of textbooks + Homework 12 Lecturing 16/17 Final Exam Examination   Required Course Resources Resource Type Resource Name Recommended Course Material(s)  Neural Networks and Learning Machines, Simon O. Haykin, 3rd Edition  Introduction to Machine Learning, Ethem Alpaydın, 2nd Edition Required Course Material(s)   Assessment Methods and Assessment Criteria Semester/Year Assessments Number Contribution Percentage     Mid-term Exams (Written, Oral, etc.) 1 70     Homeworks/Projects/Others 13 30 Total 100 Rate of Semester/Year Assessments to Success 40   Final Assessments 100 Rate of Final Assessments to Success 60 Total 100   Contribution of the Course to Key Learning Outcomes # Key Learning Outcome Contribution* 1 Reaches wide and deep knowledge through scientific research in the field of computer engineering, evaluates, implements, and comments. 4 2 Describes and uses information hidden in limited or missing data in the field of computer engineering by using scientific methods and integrates it with information from various disciplines. 5 3 Follows new and emerging applications of computer engineering profession, if necessary, examines and learns them 5 4 Develops methods and applies innovative approaches in order to formulate and solve problems in computer engineering. 5 5 Proposes new and/or original ideas and methods in the field of computer engineering in developing innovative solutions for designing systems, components or processes. 5 6 Designs and implements analytical modeling and experimental research and solves the complex situations encountered in this process in the field of Computer Engineering 5 7 works in multi disciplinary teams and takes a leading role and responsibility. 2 8 Learns at least one foreign language at the European Language Portfolio B2 level to communicate orally and written 0 9 Presents his/her research findings systematically and clearly in oral and written forms in national and international meetings. 4 10 Describes social and environmental implications of engineering practice. 0 11 Considers social, scientific and ethical values in collection, interpretation and announcement of data. 2 12 Acquires a comprehensive knowledge about methods and tools of computer engineering and their limitations. 3 * Contribution levels are between 0 (not) and 5 (maximum).   Student Workload - ECTS Works Number Time (Hour) Total Workload (Hour) Course Related Works     Class Time (Exam weeks are excluded) 14 3 42     Out of Class Study (Preliminary Work, Practice) 12 3 36 Assesment Related Works     Homeworks, Projects, Others 13 2 26     Mid-term Exams (Written, Oral, etc.) 1 24 24     Final Exam 1 30 30 Total Workload: 158 Total Workload / 25 (h): 6.32 ECTS Credit: 6