| Course Objectives: |
The course "Artificial Intelligence" offers a captivating journey into the realm of AI, tailored for students pursuing their master’s degree. Artificial Intelligence is at the forefront of technological advancements, empowering machines to emulate human intelligence and make informed decisions. Spanning a 14-week semester, this course provides an in-depth exploration of the core principles and techniques in AI. Starting with an introduction to AI and its impact on society, students delve into problem-solving methods and search algorithms. They uncover the intricacies of knowledge representation using logic and delve into the realm of uncertainty through probabilistic reasoning. As the course progresses, students venture into the realm of machine learning, where they gain practical experience with supervised and unsupervised learning algorithms. They immerse themselves in the world of neural networks and deep learning, unlocking the potential of convolutional and recurrent neural networks. The course further delves into reinforcement learning, providing students with the tools to develop intelligent agents capable of learning from their environment. NLP and computer vision take center stage, enabling students to analyze and process natural language and images. From exploring the realm of AI in robotics to ethical considerations and emerging trends, this course equips students with a holistic understanding of AI's capabilities and challenges. Throughout the journey, hands-on projects and practical exercises enable students to apply their knowledge and develop cutting-edge AI applications. By the end of the course, students emerge as skilled AI practitioners, prepared to embark on a future where intelligent systems shape the world around us. |
| Course Content: |
Introduction to AI, Intelligent Agents, Solving Problems by Searching: Uninformed Search, Informed Search, Adversarial Search and Game Playing, Machine Learning: Overview, Classification and Model Evaluation, Linear and Logistic Regression, Neural Networks, Deep Learning, Constraint Satisfaction Problems (CSPs), Markov Decision Processes, Reinforcement Learning, Logical Agents, AI Applications. |
| Week |
Subject |
Related Preparation |
| 1) |
Introduction to Artificial Intelligence
- Overview of AI and its applications
- Historical development of AI
- AI ethics and societal impact
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 2) |
Problem-Solving and Search Algorithms
- Problem formulation and state-space representation
- Uninformed search algorithms: BFS, DFS
- Heuristic search algorithms: A* Search
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 3) |
Adversarial Search and Game Playing
- Minimax algorithm
- Alpha-Beta Pruning
- Evaluation functions for game-playing agents
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 4) |
Knowledge Representation and Logic
- Propositional and Predicate Logic
- Knowledge representation using First-Order Logic
- Resolution and Inference in logic
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 5) |
Uncertainty and Probabilistic Reasoning
- Bayesian networks
- Probabilistic inference using Bayes' theorem
- Decision networks and utility theory
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 6) |
Machine Learning Fundamentals
- Supervised learning and unsupervised learning
- Regression and classification algorithms
- Evaluation metrics for ML models
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 7) |
Neural Networks and Deep Learning
- Neural network architectures
- Backpropagation algorithm
- Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs)
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 8) |
Midterm Exam |
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 9) |
Reinforcement Learning
- Markov Decision Processes (MDPs)
- Q-learning and Value Iteration
- Policy Gradient methods
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 10) |
Natural Language Processing (NLP)
- Text preprocessing and tokenization
- Sentiment analysis and text classification
- Sequence-to-sequence models for machine translation
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 11) |
Computer Vision and Image Processing
- Image feature extraction
- Object detection and recognition
- Image segmentation and image generation
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 12) |
AI in Robotics
- Robot kinematics and motion planning
- Localization and Simultaneous Localization and Mapping (SLAM)
- Reinforcement learning for robotic control
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 13) |
AI Ethics and Future Trends
- Ethical considerations in AI development and deployment
- AI in industry and research
- Emerging trends in Artificial Intelligence
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| 14) |
Final Exam
This course content covers a wide range of AI topics, from problem-solving and search algorithms to machine learning, deep learning, and AI in robotics. Each week focuses on specific AI subdomains, allowing students to gain a comprehensive understanding of the field. Hands-on projects and practical exercises are incorporated throughout the course to provide students with practical experience in AI applications.
|
Artificial Intelligence: A Modern Approach (AIMA), 4th Edition, Stuart J. Russell, Peter Norvig, Prentice Hall, 2020.
http://aima.cs.berkeley.edu/ |
| |
Program Outcomes |
Level of Contribution |
| 1) |
Ability to reach wide and deep knowledge through scientific research in the field of Computer Science and Engineering, evaluate, interpret and apply. |
|
| 2) |
Ability to use scientific methods to cover and apply limited or missing knowledge, and to integrate the knowledge of different disciplines. |
|
| 3) |
Ability to construct Computer Science and Engineering problems, develop methods to solve the problems and use innovative methods in the solution. |
|
| 4) |
Ability to develop new and/or original ideas and algorithm; develop innovative solutions in the design of system, component or process. |
|
| 5) |
Ability to have extensive knowledge about current techniques and methods applied in Computer Engineering and their constraints. |
|
| 6) |
Ability to design and implement analytical modeling and experimental research, solve and interpret complex situations encountered in the process. |
|
| 7) |
Ability to use a foreign language (English) at least at the level of
European Language Portfolio B2 in verbal and written communication. |
|
| 8) |
Ability to lead in multidisciplinary teams, develop solutions to complex situations and take responsibility. |
|
| 9) |
Awareness of the social, legal, ethical and moral values, and the ability to conduct research and implementation work within the framework of these values. |
|
| 10) |
Awareness of the new and emerging applications in Computer Science and Engineering field, and the ability to examine them and learn if necessary. |
|