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

Course Description Course Name : Introduction to Neural Networks Course Code : EE-589 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. TURGAY İBRİKÇİ Learning Outcomes of the Course : Knows basic neural network architecture Knows basic learning algorithms Understands data pre and post processing Knows training, verification and validation of neural network models Uses Artificial Neural Networks in Engineering Applications Mode of Delivery : Face-to-Face Prerequisites and Co-Prerequisites : None Recommended Optional Programme Components : None Aim(s) of Course : To introduce fundamental concepts of neural networks and study several network models in details. After taking this course, the students will be ready to understand the structure, design, and training of various types of neural networks and will be ready to apply them to the solution of problems in a variety of domains. Course Contents : In this course, the students will be introduced to various neural networks models and algorithms. Several applications of neural networks will be studied including bioinformatics and special topics that the students are interested in. Language of Instruction : English Work Place : Classroom   Course Outline /Schedule (Weekly) Planned Learning Activities Week Subject Student's Preliminary Work Learning Activities and Teaching Methods 1 Introduction Reading Course Notes Presentation 2 Network Architectures and MatLab Basics Reading Course Notes Presentation 3 Rosenblatt´s Perceptron Reading Course Notes Presentation 4 Multilayer Perceptrons Reading Course Notes Presentation 5 Backpropagation Learning Algorithm Reading Course Notes Presentation 6 Kernel Methods and Radial Basis Function Networks Reading Course Notes Presentation 7 Support Vector Machines Reading Course Notes Presentation 8 Midterm Study all previous topics Exam 9 Self-Organizing Networks, Learning Vector Quantization Reading Course Notes Presentation 10 İstatistik Mekanik Kökenli Stokastik Yöntemler. Reading Course Notes Presentation 11 Neurodynamics Reading Course Notes Presentation 12 Bayesian Learning Reading Course Notes Presentation 13 Recurrent Networks Reading Course Notes Presentation 14 Presentations of Projects-I Reading Course Notes Presentation 15 Presentations of Projects-II Reading Course Notes Presentation 16/17 Final Exam Study all previous topics Exam   Required Course Resources Resource Type Resource Name Recommended Course Material(s)  Neural Networks and Learning Machines, Simon HAYKIN, Prentice Hall (2008) Required Course Material(s)  Sources of Internet   Assessment Methods and Assessment Criteria Semester/Year Assessments Number Contribution Percentage     Mid-term Exams (Written, Oral, etc.) 1 20     Homeworks/Projects/Others 4 80 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 Communicates with people in an appropriate language and style. 3 2 Specializes by furthering his knowledge level at least in one of the basic subfields of electiral-electronic engineering. 2 3 Grasps the integrity formed by the topics involved in the field of specialization. 4 4 Grasps and follows the existing literature in the field of specialization. 4 5 Comprehends the interdisciplinary interaction of his field with other fields. 4 6 Has the aptitude to pursue theoretical and experimental work. 5 7 Forms a scientific text by compiling the knowledge obtained from research. 4 8 Works in a programmed manner within the framework set by the advisor on the thesis topic, in accordance with the logical integrity required by this topic. 5 9 Performs a literature search in scientific databases; in particular, to scan the databases in an appropriate manner, to list and categorize the listed items. 4 10 Has English capability at a level adequate to read and understand a scientific text in his field of specialization, written in English. 3 11 Compiles his/her knowledge in his/her field of specialization. in a presentation format, and presents in a clear and effective way. 4 12 Writes a computer code aimed at a specific purpose, in general, and related with his/her field of specialization, in particular 4 13 Pursues research ın new topics based on his/her existing research experıence. 2 14 Gives guidance in environments where problems related with his/her field need to be solved, and takes initiative. 5 15 Develops and evaluates projects, policies and processes in his field of specialization. 1 * 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 4 56     Out of Class Study (Preliminary Work, Practice) 5 5 25 Assesment Related Works     Homeworks, Projects, Others 4 10 40     Mid-term Exams (Written, Oral, etc.) 1 10 10     Final Exam 1 20 20 Total Workload: 151 Total Workload / 25 (h): 6.04 ECTS Credit: 6