DATS5017 Explainable, Responsible and Trustworthy AIIstinye UniversityDegree Programs Data Science (Master) (with Thesis) (English)General Information For StudentsDiploma SupplementErasmus Policy StatementNational Qualifications
Data Science (Master) (with Thesis) (English)

Preview

Master TR-NQF-HE: Level 7 QF-EHEA: Second Cycle EQF-LLL: Level 7

Course Introduction and Application Information

Course Code: DATS5017
Course Name: Explainable, Responsible and Trustworthy AI
Semester: Fall
Course Credits:
ECTS
6
Language of instruction: English
Course Condition:
Does the Course Require Work Experience?: No
Type of course: Departmental Elective
Course Level:
Master TR-NQF-HE:7. Master`s Degree QF-EHEA:Second Cycle EQF-LLL:7. Master`s Degree
Mode of Delivery: Face to face
Course Coordinator: Araş. Gör. KAZIM TİMUÇİN UTKAN
Course Lecturer(s):
Course Assistants:

Course Objective and Content

Course Objectives: In this course, students will gain an in-depth understanding of the emerging themes of explainability, responsibility and trustworthiness in Artificial Intelligence (AI) and learn how to design systems in accordance with these principles. The course will focus on techniques to make AI models understandable to humans, emphasize the practice of responsible algorithm development in the light of ethical standards and regulatory legislation, and learn how to integrate trustworthiness considerations. Students will be able to evaluate the societal impact and responsibilities of the applications they develop.
Course Content: 1. Introduction and importance of the concepts of Explainable Artificial Intelligence (XAI).
2. Principles of responsible AI and ethical frameworks.
3. Trustworthy Artificial Intelligence system design and security standards.
4. Practical review of XAI methods and techniques.
5. Social and legal aspects of responsible and trustworthy AI systems.

Learning Outcomes

The students who have succeeded in this course;
1) 1. To be able to explain the basic principles and techniques of XAI.
2) 2. Identify ethical guidelines for responsible AI design.
3) 3. Understand the criteria for designing reliable Artificial Intelligence systems.
4) 4. Apply explainability methods for various AI models.
5) 5. Evaluate the social, legal and ethical implications of Artificial Intelligence systems.

Course Flow Plan

Week Subject Related Preparation
1) Introduction: What is Explainable Artificial Intelligence? Why is it important? -
2) Explainable Artificial Intelligence models and approaches. -
3) XAI through decision trees, rules and linear models. .
4) Deep learning and interpretability: SHAP, LIME methods. .
5) Reliable Artificial Intelligence design principles and use cases. -
6) Artificial Intelligence ethics: Ethics in automated decision making systems. -
7) The place of AI systems in legal regulations and GDPR. -
8) midterm exam -
9) Visualization techniques and tools for XAI. .
10) Responsible Artificial Intelligence: Stakeholder and user involvement. -
11) Evaluating the responsibility and impact of algorithms. -
12) XAI applications through Kasus studies. -
13) Security and privacy: Ensuring security in AI systems. -
14) Trusted AI and pre-release audits. -
15) Student presentations and project development. -
16) final exam

Sources

Course Notes / Textbooks: Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
References: Explainable AI: Interpreting, Explaining and Visualizing Deep Learning

Course - Program Learning Outcome Relationship

Course Learning Outcomes

1

2

3

4

5

Program Outcomes
1) Students who successfully complete this program, Knows the scope of technical applications of data science and the tools that can be used. 2 2 3 3 3
2) Students who successfully complete this program, Knows the effects of application results on society-culture-law. 3 3 3 2 2
3) Students who complete this program; Recognize the mathematics and code in application processes 2 2 2 2 2
4) Students who complete this program; Explain the effects of the processes in data science on the output and the individual 2 3 2 3 2
5) Students who successfully complete this program, Understands the insight-foresight and foresight created by data science as a whole in the face of a certain discipline/case. 3 2 2 2 3

Course - Learning Outcome Relationship

No Effect 1 Lowest 2 Average 3 Highest
       
Program Outcomes Level of Contribution
1) Students who successfully complete this program, Knows the scope of technical applications of data science and the tools that can be used. 2
2) Students who successfully complete this program, Knows the effects of application results on society-culture-law. 2
3) Students who complete this program; Recognize the mathematics and code in application processes 3
4) Students who complete this program; Explain the effects of the processes in data science on the output and the individual 3
5) Students who successfully complete this program, Understands the insight-foresight and foresight created by data science as a whole in the face of a certain discipline/case. 2

Assessment & Grading

Semester Requirements Number of Activities Level of Contribution
Midterms 1 % 40
Final 1 % 60
total % 100
PERCENTAGE OF SEMESTER WORK % 40
PERCENTAGE OF FINAL WORK % 60
total % 100

Workload and ECTS Credit Calculation

Activities Number of Activities Workload
Course Hours 14 42
Midterms 8 29
Final 8 78
Total Workload 149