TYPE OF COURSE UNIT	Elective Course
LEVEL OF COURSE UNIT	Bachelor's Degree
YEAR OF STUDY	-
SEMESTER	-
NUMBER OF ECTS CREDITS ALLOCATED	5
NAME OF LECTURER(S)	-
LEARNING OUTCOMES OF THE COURSE UNIT	At the end of this course, the students; 1) Employ known algorithms to solve given problems 2) Use software tools 3) Develop critical thinking skills 4) Propose and design new systems, by extending existing algorithms or exploring novel approaches, to meet the given requirements
MODE OF DELIVERY	Face to face
PRE-REQUISITES OF THE COURSE	No
RECOMMENDED OPTIONAL PROGRAMME COMPONENT
COURSE DEFINITION
COURSE CONTENTS	WEEK TOPICS 1st Week Introduction, course structure, overview of machine learning and deep learning. 2nd Week Optimization. 3rd Week Feedforward networks and training. 4th Week Feedforward networks and training; 5th Week Convolutional neural networks. 6th Week Convolutional neural networks. 7th Week Deep learning for spatial localization. 8th Week Midterm 9th Week Recurrent neural networks. 10th Week Recurrent neural networks. 11th Week Deep generative models. 12th Week Deep generative models. 13th Week Deep reinforcement learning. 14th Week Deep reinforcement learning. Project presentations.
RECOMENDED OR REQUIRED READING	Deep Learning, I. Goodfellow, Y. Bengio, A. Courville, 2016, MIT Press
PLANNED LEARNING ACTIVITIES AND TEACHING METHODS	Lecture
ASSESSMENT METHODS AND CRITERIA	Quantity Percentage(%) Mid-term 1 30 Project 1 30 Total(%) 60 Contribution of In-term Studies to Overall Grade(%) 60 Contribution of Final Examination to Overall Grade(%) 40 Total(%) 100
ECTS WORKLOAD	Activities Number Hours Workload Midterm exam 1 2 2 Preparation for Quiz Individual or group work 14 3 42 Preparation for Final exam 1 25 25 Course hours 14 3 42 Preparation for Midterm exam 1 25 25 Laboratory (including preparation) Final exam 1 2 2 Homework Project 1 12 12 Total Workload 150 Total Workload / 30 5 ECTS Credits of the Course 5
LANGUAGE OF INSTRUCTION	Turkish
WORK PLACEMENT(S)	No