Course Overview

• Course Code: CSC 441
• Course Title: Artificial Intelligence
• Instructor: Dr. Sara Abdelghafar, Assistant Professor of Computer Science, Canadian International College (CIC)
• Grading Method:
  • Mid Term Examination: 25%
  • Practical Assignments and Quizzes: 25%
  • Final Examination: 50%

What is Artificial Intelligence?

• Definition:
  • AI is a branch of computer science focused on creating machines capable of performing tasks requiring human-like intelligence, such as learning, reasoning, and language understanding.
  • Examples: Chess-playing computers, self-driving cars.

The History of AI

• Approaches to AI:
  • Acting Humanly: Turing Test (Alan Turing, 1950) - A machine is considered intelligent if it can deceive a human into thinking it is human. Components include:
  • Knowledge
  • Reasoning
  • Language Understanding
  • Learning
  • Systems Thinking Approaches:
  • Systems that think like humans
  • Systems that act humanly
  • Systems that think rationally
  • Systems that act rationally

Parent Disciplines of AI

• Philosophy
• Cognitive Science
• Mathematics
• Psychology
• Computer Science

Applications of AI

• Areas of Application:
  • Self-Driving Cars
  • Chatbots
  • Gaming
  • Computer Vision Systems
  • Expert Systems
  • Intelligent Robots
  • Recommendation Systems
  • Internet of Things (IoT)
  • Generative AI

AI in Self-Driving Cars

• Function:
  • Operate without human intervention using sensors, cameras, radar, GPS, and AI algorithms.
  • Role of AI:
  • Perceiving environment
  • Decision-making
  • Controlling movement
  • Learning:
  • Utilizes machine learning to improve behavior over time.

AI in Chatbots and Virtual Assistants

• Natural Language Processing (NLP):
  • Enables chatbots to understand and respond to human language.
  • Examples:
  • Amazon Alexa, Google Assistant

AI in Gaming

• Enhancements:
  • Improved Non-Player Character (NPC) behavior
  • Dynamic and personalized gaming experiences
  • Predictive environments adjusting to player behavior

AI in Computer Vision Systems

• Function:
  • Enables machines to interpret visual information.
  • Processes:
  • Image acquisition
  • Preprocessing
  • Object detection
  • Applications:
  • Autonomous vehicles, medical imaging, surveillance.

AI in Robotics

• Use of Sensors:
  • AI-powered robots use sensors to detect real-world data.
  • Applications in factories, homes, and hospitals.
  • Examples:
  • Robot vacuum cleaners (Roomba), Amazon delivery robots

AI in Recommendation Systems

• Personalization:
  • Recommend products or content based on past behavior.
  • Examples:
  • Netflix recommendations, Amazon product suggestions

AI in the Internet of Things (IoT)

• Overview:
  • Systems that learn and emulate human tasks autonomously.
  • Role of AI:
  • Analyze data collected from interconnected devices to derive actionable insights.

AI in Smart Homes

• Functionality:
  • Devices learn user preferences to automate tasks, e.g., adjusting lighting or temperature.
  • Examples:
  • Amazon Alexa, Google Nest

Generative AI

• Function:
  • Creates content like text, images, and music based on input.
  • Examples:
  • ChatGPT, DALL·E

AI in Deepfake Detection

• Technology:
  • Detects manipulated videos using AI techniques.
  • Risks and Tools:
  • Misinformation risks; AI tools analyze videos for inconsistencies.

Aspects of Intelligence in AI

• Components:
  • Reasoning
  • Perception
  • Linguistic Intelligence
  • Problem Solving
  • Learning

Reasoning

• Types:
  • Inductive: Generalizes from specific instances
  • Deductive: Applies general principles to specific cases
• Example:
  • Expert systems solve problems through reasoning based on a knowledge base.

Expert Systems

• Definition:
  • Simulates human decision-making based on a knowledge base and inference rules.
  • Components:
  • Knowledge Base (KB)
  • Inference Engine
• Characteristics:
  • High performance, understandable responses, and limited domains.

Perception

• Definition:
  • Machines interpreting sensory input (e.g., cameras in self-driving cars).

Linguistic Intelligence

• Function:
  • AI’s ability to process and understand natural language via NLP.

Problem Solving

• Process:
  • Analyzing problems, identifying patterns, and using algorithms for solutions (e.g., search algorithms).

Learning

• Overview:
  • Machines improve performance through data.
  • Types of Learning:
  • Direct Instruction
  • Problem Solving Learning
  • Explanation Based Learning (EBL)
• Machine Learning (ML):
  • A key branch of AI involving algorithms that enable self-learning from data.
  • Key Techniques:
  • Artificial Neural Networks (ANNs)

Contact Information

• Instructor's Email: sara_abdelghafar@cic-cairo.com

Good Luck!

• Best Wishes for Your Exams!
• Dr. Sara Abdelghafar