|
|
| YZLI7060 | Data Driven Inference and Cloud Based Artificial Intelligence | 3+0+0 | ECTS:7.5 | | Year / Semester | Spring Semester | | Level of Course | Second Cycle | | Status | Elective | | Department | DEPARTMENT of SOFTWARE ENGINEERING | | Prerequisites and co-requisites | None | | Mode of Delivery | | | Contact Hours | 14 weeks - 3 hours of lectures per week | | Lecturer | Dr. Öğr. Üyesi Mustafa Hakan BOZKURT | | Co-Lecturer | | | Language of instruction | | | Professional practise ( internship ) | None | | | | The aim of the course: | | Examine and apply the approaches related with -Business intelligence and data visualization, statistics and data analysis for business; Machine learning and deep learning approaches used in data-driven inference; Data solutions in cloud technology, practical applications of data-driven inference. |
| Programme Outcomes | CTPO | TOA | | Upon successful completion of the course, the students will be able to : | | | | PO - 1 : | Understand basic concepts of data-driven inference and statistics. | 1,3,4,6 | 1,6, | | PO - 2 : | Have knowledge about data interpretation and visualization. | 1,3,4,6 | 1,6, | | PO - 3 : | Have basic knowledge about data analysis in cloud environment. | 1,3,4,6 | 1, | | PO - 4 : | Design inference based on data with deep learning concepts. | 1,3,4,6 | 1,6, | | CTPO : Contribution to programme outcomes, TOA :Type of assessment (1: written exam, 2: Oral exam, 3: Homework assignment, 4: Laboratory exercise/exam, 5: Seminar / presentation, 6: Term paper), PO : Learning Outcome | | |
| Introduction and mathematical foundations of data-driven inference. Statistics and business intelligence. Data pre-processing and approaches to collecting data from different sources. Meta learning and deep learning techniques used in data science. Artificial intelligence solutions in cloud technology. Analyzing solutions on different and current problems. |
| |
| Course Syllabus | | Week | Subject | Related Notes / Files | | Week 1 | Mathematical/Statistical foundations | | | Week 2 | Hypothesis and inference | | | Week 3 | Business Intelligence | | | Week 4 | Data acquisition techniques | | | Week 5 | Data preparation and preprocessing | | | Week 6 | Challenges in data-driven inference and machine learning solutions | | | Week 7 | Using deep learning models for data-driven inference | | | Week 8 | Design/optimization of deep learning models | | | Week 9 | MIDTERM EXAM HAFTASI | | | Week 10 | Deep learning inference application | | | Week 11 | Deep learning inference application | | | Week 12 | Deep learning inference application | | | Week 13 | Reinforcement Learning | | | Week 14 | Artificial Intelligence Technologies in the Cloud | | | Week 15 | Evaluation of data-driven inference outputs | | | Week 16 | FINAL EXAM | | | |
| 1 | Inference and Learning from Data: Volume 1: Foundations / Ali H. Sayed | | | 2 | Deep Learning/ Ian Goodfellow, Aaron Courville, Yoshua Bengio | | | 3 | Visualizing Google Cloud: 101 Illustrated References for Cloud Engineers and Architectsi Priyanka Vergadia | | | |
| 1 | Grokking Deep Reinforcement Learning/Miguel Morales | | | 2 | Deep Learning with Python/François Chollet | | | 3 | Python Data Science Handbook: Essential Tools for Working with Data / Jake VanderPlas | | | |
| Method of Assessment | | Type of assessment | Week No | Date | Duration (hours) | Weight (%) | | Mid-term exam | 9 | | 2 | 20 | | Homework/Assignment/Term-paper | 15 | | 2 | 30 | | End-of-term exam | 16 | | 2 | 50 | | |
| Student Work Load and its Distribution | | Type of work | Duration (hours pw) | No of weeks / Number of activity | Hours in total per term | | Yüz yüze eğitim | 3 | 14 | 42 | | Sınıf dışı çalışma | 6 | 14 | 84 | | Ödev | 3 | 14 | 42 | | Dönem sonu sınavı için hazırlık | 4 | 3 | 12 | | Dönem sonu sınavı | 3 | 1 | 3 | | Total work load | | | 183 |
|