Artificial Intelligence Course Quiz

AI310 & CS361 Artificial Intelligence Course Introduction & Plan

• This course is for mainstream, medical informatics, and software engineering programs.
• Tentative topics and learning objectives are planned.
• Course logistics and grading policy are outlined.
• Details on effective classroom conduct and academic integrity are included.
• An academic agenda, including the weekly schedule of topics to be covered, is given.

Course Details

• Course code(s): AI301 and CS361
• Course name: Artificial Intelligence
• Coordinating unit: Department of Artificial Intelligence and Department of Computer Science, Faculty of Computers & Artificial Intelligence, Helwan University.
• Term: Semester 1 [Fall]
• Level: Undergraduate - Level 3

Tentative Topics & Learning Objectives

• The course gives a basic introduction to Artificial Intelligence (AI) and Machine Learning (ML).
• Students learn about philosophical fundamental problems, ethical questions, and the field's history.
• Key topics of knowledge representation, reasoning, and learning will be covered.
• Topics will also include introductions to machine learning, probabilistic reasoning, and applications like robotics, computer vision, and natural language processing.
• Basic supervised classification techniques (e.g., Artificial Neural Networks) and unsupervised learning (Clustering), optimization (Evolutionary Algorithms), and regression, are also covered.
• Students gain practical understanding through implementations of the algorithms.

Topics Covered (Tentative)

• Main approaches to AI & Learning
• Task environment
• Performance measures
• Intelligent Agents
• Knowledge Representation
• Problem solving by searching
• Uninformed Search
• Informed Search
• Adversarial Search
• Beyond classical search: Evolutionary Algorithms
• Machine learning (ML)
• Supervised Learning versus Unsupervised Learning
• Decision Trees
• Artificial Neural Networks: Perceptrons, & Multi-Layer Perceptrons
• Support Vector Machines
• Clustering Algorithms
• Ensemble Learning
• Selected AI / ML Applications

Recommended Background

• Prerequisites for this course include an Introduction to Computer Science, Introduction to Programming Languages 1 & 2 (including Object-Oriented Programming), and Data Structures & Algorithms.
• Experience with Python/MATLAB, probability, statistics, and linear algebra is recommended, but not required.

Course Logistics

• Announcements & Course Materials
• Additional Resources (per section)
• Assessment Summary (Grading Policy)
• Exercises .. What have we learned?
• Be an Effective Learner ..?
• Classroom Code of Conduct
• Academic Integrity & Plagiarism

Announcements & Course Materials

• Video Lessons: All recorded lectures are available on the Amr S. Ghoneim YouTube Channel and a CS361 Introduction to Artificial Intelligence YouTube Playlist.
• Downloads, Homework, & Announcements: All course material (lecture notes, assignments, any supplemental notes), will be provided online on a weekly basis. The materials are hosted on a Google Drive folder.
• Required Resources: - Stuart J. Russell and Peter Norvig, "Artificial Intelligence: A Modern Approach" (2010) - George F. Luger, "Artificial Intelligence: Structures and strategies for complex problem solving" (2005)
• Additional Textbooks - Wolfgang Ertel, "Introduction to Artificial Intelligence," - Miroslav Kubat, "An Introduction to Machine Learning," - Y. Abu-Mostafa, M. Magdon-Ismail, & H-T. Lin, "Learning from Data - A Short Course" - Max Bramer, "Principles of Data Mining"

Assessment Summary (Grading Policy)

• Final Written Exam: 50%
• Group Project: 35%
• Midterm Written Exam: 15%
• Attendance and Participation during labs are mandatory.

Class Project

• Students work in groups of 5–6 on a real-world domain.
• Final reports include presentations, analysis, and project results.
• Demos are required (~15 minutes).
• Focus on real-world data problems.

Exercises (What have we learned?)

• Key aspects of the topics discussed in each lecture are reviewed with exercises.
• Exercises are expected to highlight learned material, emphasize key information, correct misunderstandings, summarize, review, and demonstrate understanding.
• Students are expected to apply knowledge to new situations.

Be an Effective Learner

• Have the desire to seek knowledge and acquire new skills.
• Ask questions.
• Be an avid reader.
• Be an attentive listener.
• Find your preferred learning style and learn in multiple ways.
• Do NOT memorize.
• Embrace discomfort.
• Practice, practice, practice (gain practical experience).
• Teach what you've learned to someone else. Use testing to boost learning Avoid multitasking. Make use of memory improvement techniques. Draw up a schedule, examine your lifestyle and create a dedicated study station.

Classroom Code of Conduct

• Punctuality and preparation are emphasized.
• Handouts and work should be well organized.
• Participation in class is encouraged.
• Respect for oneself, teachers, and classmates is essential.
• Turn off mobile phones or set them to silent mode before entering.
• Adopt a positive professional attitude.
• Independent study is crucial (about 6–8 hours per week).
• Completed homework should be submitted on time.
• University/Faculty facilities (e.g. libraries) and online resources should be utilized.
• Adhere to University regulations.
• Understand all aspects of the required format for assignments and assessments.
• Maintain academic integrity and avoid plagiarism.

Academic Integrity & Plagiarism

• Discuss ideas and methodology with the class; independently write solutions for assignments and projects.
• Code-checking is employed to identify similar submissions or those using code from other sources.
• properly cite all code snippets from external sources.

Academic Agenda (Tentative Schedule)

• Weekly topics are listed, including schedules for exams and projects, which are to be determined by the faculty.

Lecture 1: Introduction to Artificial Intelligence

• Discusses intelligence and AI foundations.
• Explores systems that act/think like humans (e.g., Turing Test, Chinese Room).
• Examines AI as the study and design of intelligent agents in the world.
• Discusses strong vs. weak AI hypotheses.

Lecture 1: Foundations of AI

• Outlines philosophical considerations in AI
• Explores connections between mathematics, economics and AI
• Introduces the concept of intelligence as related to ability for problem solving

Additional Resources (Various Lectures)

• Numerous YouTube links for additional learning resources are provided throughout the course material regarding the topics covered, including videos from various instructors and institutions on AI topics, which are frequently updated.

Additional Information

• Additional details on the various topics are provided in the supplementary materials. This includes, but is not limited to; exercises from the lecture, additional resources, and important links to further understanding.