1.

Course Information
• Course Code: SEN4210
• Course Title: Introduction to Artificial Intelligence Systems
• Credits: 3 Credits
• Contact Hours: 30 hours (20 hours of lectures, 5 hours of tutorials, 5 hours of practical
sessions)
• Prerequisites: Basic knowledge of programming, data structures, and algorithms.
• Target Audience: Graduate students in M.Sc. Information Systems, Computer Science
majors, and non-specialists with a suitable background.

2. Course Objectives
By the end of this course, students will be able to:
1. Understand Core AI Principles:
• Gain a comprehensive understanding of the fundamental concepts and principles of
Artificial Intelligence (AI).
• Explore the historical development and evolution of AI.
2. Master AI Techniques:
• Acquire in-depth knowledge of key AI techniques, including search algorithms,
knowledge representation, and reasoning.
• Learn about advanced topics such as machine learning, natural language processing,
and computer vision.
3. Apply AI in Real-World Scenarios:
• Develop the ability to apply AI techniques to solve complex problems in various
domains.
• Understand the practical implications and applications of AI in industry and research.
4. Critically Analyze AI Developments:
• Critically assess current trends and developments in AI.
• Engage in discussions and debates on the ethical, social, and economic implications
of AI technologies.
5. Prepare for Advanced Research and Industry Roles:
• Build a strong foundation for further research in AI or related fields.
• Equip students with the skills necessary for careers in AI-intensive industries, such as
software development, data science, and AI research.

3. Course Content

Week 1-2: Introduction to Artificial Intelligence

• Topics:
• History and evolution of AI.
• Overview of AI subfields: Machine Learning, Natural Language Processing,
Computer Vision, Robotics.
• AI applications in various industries.
• Learning Outcomes:
• Understand the scope and importance of AI.
• Recognize the different branches of AI and their applications.
Week 3-4: Search Algorithms
• Topics:
• Problem spaces and search.
• Uninformed search methods: Depth-First Search (DFS), Breadth-First Search (BFS).
• Informed search methods: A*, Heuristic functions.
• Game trees and adversarial search: Minimax algorithm, Alpha-Beta pruning.
• Learning Outcomes:
• Implement basic search algorithms.
• Evaluate the performance and suitability of different search techniques.

Week 5-6: Knowledge Representation and Reasoning

• Topics:
• Logic-based representations: Propositional logic, First-Order Logic (FOL).
• Inference and resolution.
• Semantic networks and frames.
• Rule-based systems.
• Learning Outcomes:
• Represent knowledge using different formalisms.
• Apply reasoning techniques to draw conclusions from knowledge bases.

Week 7-8: Planning

• Topics:
• Classical planning problems.
• Planning as search.
• Hierarchical planning.
• Partial-order planning.
• Learning Outcomes:
• Formulate planning problems and solve them using AI techniques.
• Understand the challenges and limitations of automated planning.

Week 9-10: Machine Learning

• Topics:
• Introduction to machine learning.
• Supervised learning: Regression, Classification.
• Unsupervised learning: Clustering, Dimensionality reduction.
• Neural networks and deep learning.
• Learning Outcomes:
• Differentiate between various machine learning paradigms.
• Implement basic machine learning algorithms.

Week 11-12: Natural Language Processing

• Topics:
• Introduction to natural language processing (NLP).
• Syntax and parsing: Context-Free Grammars (CFG), Transition Networks.
• Semantics and meaning representation.
• Applications of NLP: Text classification, Sentiment analysis.
• Learning Outcomes:
 • Understand the challenges of processing natural language.
• Apply basic NLP techniques to text data.

Week 13-14: Computer Vision

• Topics:
• Introduction to computer vision.
• Image processing fundamentals.
• Feature extraction and object recognition.
• Applications of computer vision: Face detection, Optical Character Recognition
(OCR).
• Learning Outcomes:
• Grasp the basics of image processing and analysis.
• Implement simple computer vision algorithms.

Week 15: Expert Systems

• Topics:
• Introduction to expert systems.
• Knowledge acquisition and representation in expert systems.
• Inference engines and rule-based reasoning.
• Case studies of expert systems in industry.
• Learning Outcomes:
• Understand the architecture and components of expert systems.
• Evaluate the strengths and weaknesses of rule-based systems.

4. Teaching and Learning Methods

• Lectures: Interactive sessions covering theoretical concepts and practical examples.
• Tutorials: Problem-solving sessions to reinforce understanding of lecture material.
• Practical Sessions: Hands-on lab work using AI tools and programming languages (e.g.,
Python, TensorFlow).
• Assignments: Individual and group assignments to apply AI techniques to real-world
problems.
• Research Project: A small-scale research project to explore a specific AI topic in depth.

5. Assessment
• Assignments: 30%
• Includes programming exercises, problem sets, and written reports.
• Midterm Exam: 20%
• Covers topics from the first half of the course.
• Research Project: 20%
• A project that involves researching, implementing, and evaluating an AI technique.
• Final Exam: 30%
• Comprehensive exam covering all course content.

6. Recommended Textbooks
• "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig.
• "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
 • "Pattern Recognition and Machine Learning" by Christopher Bishop.

7. Additional Resources
• Online Courses:
• Coursera's "Machine Learning" by Andrew Ng.
• edX's "Introduction to Artificial Intelligence" by MIT.
• Research Papers:
• Selected papers from AI conferences such as NeurIPS, ICML, and CVPR.
• Software Tools:
• Python libraries: TensorFlow, PyTorch, scikit-learn.
• NLP tools: NLTK, spaCy.

8. Course Policies
• Attendance: Regular attendance is expected. More than three absences may affect your
grade.
• Academic Integrity: All work must be original. Plagiarism will not be tolerated.
• Late Submissions: Assignments submitted late will incur a penalty unless prior
arrangements are made.
Unit1: Introduction to Artificial Intelligence

I. History and Evolution of Artificial Intelligence (AI)

The history of Artificial Intelligence (AI) is a fascinating journey marked by significant milestones,
groundbreaking ideas, and evolving philosophies. Understanding this history provides crucial
context for the current state and future potential of AI technologies.

1. Early Concepts and Foundations (Antiquity to 1940s)

• Ancient Myths and Philosophy:
• The concept of artificial beings with intelligence dates back to ancient myths and
philosophical discussions.
• Examples:
• Greek Mythology: Talos, a giant automaton made of bronze, was said to
guard the island of Crete.
• Jewish Mythology: The Golem, an animated anthropomorphic being created
entirely from inanimate matter.
• Philosophical Contributions:
• René Descartes (1596–1650): Proposed that the body is a machine and that the mind
is separate, introducing the mind-body problem.
• Thomas Hobbes (1588–1679): Suggested that reasoning is like numerical
computation, laying the groundwork for symbolic AI.
• Gottfried Wilhelm Leibniz (1646–1716): Envisioned a universal language and
calculus of reasoning, which influenced symbolic logic.
• Early Mechanical Devices:
 • Mechanical Calculators: Devices like Blaise Pascal's Pascaline (1642) and
Gottfried Leibniz's Stepped Reckoner (1673) demonstrated early forms of automated
computation.
• Automata: Mechanical devices designed to mimic human actions, such as Jacques
de Vaucanson's mechanical duck (1739), which could flap its wings and eat grain.

2. Birth of AI as a Field (1940s to 1956)

• Development of Computers:
• ENIAC (1945): One of the first general-purpose electronic computers, marking the
beginning of the computer age.
• Turing Machine (1936): Alan Turing's theoretical construct laid the foundation for
modern computer science and the concept of algorithmic computation.
• Turing Test (1950):
• Alan Turing proposed the "Imitation Game," now known as the Turing Test, as a
criterion for determining whether a machine could exhibit intelligent behavior
indistinguishable from that of a human.
• Dartmouth Conference (1956):
• Widely considered the birthplace of AI as a field.
• Organized by John McCarthy, Marvin Minsky, Nathaniel Rochester, and Claude
Shannon.
• The term "Artificial Intelligence" was coined at this conference.
• Participants discussed the potential of machines to simulate human intelligence,
including learning, reasoning, and language processing.

3. The Golden Age of AI (1956 to 1974)

• Symbolic AI and Expert Systems:
• Logic Theorists (1955): Developed by Allen Newell and Herbert A. Simon, it was
the first AI program designed to mimic human problem-solving.
• General Problem Solver (GPS): Another program by Newell and Simon, aimed at
solving a wide range of problems using logical reasoning.
• Natural Language Processing:
• ELIZA (1964): A program by Joseph Weizenbaum that simulated a conversation
with a human, using pattern matching and substitution to give the illusion of
understanding.
• Perceptrons:
• Perceptron (1957): A simple neural network model developed by Frank Rosenblatt,
capable of learning from data.
• AI Languages:
• LISP (1958): Developed by John McCarthy, it became the dominant AI
programming language due to its ability to manipulate symbolic expressions.
4. The AI Winter (1974 to 1980s)
• Funding Cuts and Disillusionment:
• The initial optimism of the 1960s gave way to skepticism as AI research faced
challenges and failed to meet high expectations.
• Challenges:
• Limited computational power.
• Difficulty in scaling up AI systems.
• Overestimation of the ability to replicate human intelligence.
• Criticisms:
• Marvin Minsky and Seymour Papert's Critique of Perceptrons (1969):
Highlighted the limitations of simple neural networks, leading to a decline in neural
network research.

5. The Rise of Expert Systems and AI Revival (1980s)

• Expert Systems:
• DENDRAL (1965): An early expert system developed at Stanford University for
chemical analysis.
• MYCIN (1970s): An expert system for diagnosing bacterial infections and
recommending antibiotics.
• AI Industry Growth:
• The development of commercial AI applications led to increased investment and
interest in AI technologies.

6. The Second AI Winter (Late 1980s to 1990s)

• Limitations of Expert Systems:
• Expert systems were found to be brittle and difficult to maintain.
• High development and maintenance costs.
• Technological and Economic Factors:
• Economic downturns led to reduced funding for AI research.
• The focus shifted to more practical and cost-effective technologies.

7. The AI Renaissance (1990s to Present)

• Machine Learning and Data-Driven Approaches:
• Statistical Learning: The rise of machine learning algorithms that learn from data,
such as Support Vector Machines (SVM) and Random Forests.
• Neural Networks Revival: Advances in computing power and the development of
deep learning techniques led to a resurgence in neural network research.
• Big Data and Computational Power:
• The availability of large datasets and increased computational power enabled the
training of complex models.
• AI in Industry:
 • AI technologies became integrated into various industries, including healthcare,
finance, and entertainment.
• Breakthroughs:
• Deep Blue (1997): IBM's chess-playing computer defeated world champion Garry
Kasparov.
• Watson (2011): IBM's AI system won the quiz show Jeopardy!.
• AlphaGo (2016): Google's AI program defeated a world champion Go player.

8. Current Trends and Future Directions

• AI Ethics and Safety:
• Growing focus on the ethical implications of AI, including bias, privacy, and
accountability.
• AI in Everyday Life:
• AI technologies are becoming ubiquitous, from virtual assistants like Siri and Alexa
to recommendation systems and autonomous vehicles.
• AI Research Frontiers:
• Artificial General Intelligence (AGI): The pursuit of AI with the ability to
understand, learn, and apply knowledge across a wide range of tasks.
• Explainable AI (XAI): Developing AI systems that can explain their decisions and
actions.

II-Overview of AI subfields: Machine Learning, Natural Language Processing, Computer

Vision, Robotics.
Artificial Intelligence (AI) is a broad field encompassing various subfields, each focusing on
different aspects of creating intelligent systems. Below is an overview of four major subfields of AI:
Machine Learning, Natural Language Processing, Computer Vision, and Robotics.

1. Machine Learning (ML)

Definition:
Machine Learning is a subset of AI that focuses on the development of algorithms and statistical
models that enable computers to perform tasks without explicit instructions. Instead, they learn
from data and improve their performance over time.
Key Concepts:
• Supervised Learning: The algorithm is trained on a labeled dataset, where the input and the
correct output are provided. The goal is to learn a mapping from inputs to outputs.
• Examples: Regression, Classification (e.g., Logistic Regression, Decision Trees,
Support Vector Machines, Neural Networks).
• Unsupervised Learning: The algorithm is trained on an unlabeled dataset, and it tries to
identify patterns or groupings within the data.
• Examples: Clustering (e.g., K-Means, Hierarchical Clustering), Dimensionality
Reduction (e.g., Principal Component Analysis, t-SNE).
 • Reinforcement Learning: The algorithm learns by interacting with an environment and
receiving feedback in the form of rewards or penalties. The goal is to maximize cumulative
rewards.
• Examples: Q-Learning, Deep Q-Networks (DQN).
Applications:
• Image and Speech Recognition: Identifying objects in images or transcribing spoken
language.
• Recommendation Systems: Suggesting products, movies, or content based on user
behavior.
• Fraud Detection: Identifying unusual patterns that may indicate fraudulent activity.
Challenges:
• Overfitting: When the model learns the training data too well and performs poorly on new
data.
• Bias and Fairness: Ensuring that models do not perpetuate or amplify existing biases in the
data.

2. Natural Language Processing (NLP)

Definition:
Natural Language Processing is a subfield of AI that focuses on the interaction between computers
and humans through natural language. The goal is to enable computers to understand, interpret, and
generate human language in a meaningful way.
Key Concepts:
• Syntax: The arrangement of words and phrases to create well-formed sentences.
• Examples: Parsing, Part-of-Speech Tagging.
• Semantics: The meaning behind the words and sentences.
• Examples: Word Sense Disambiguation, Semantic Role Labeling.
• Pragmatics: The context and implications of language use.
• Examples: Understanding sarcasm, context-dependent meanings.
Techniques:
• Tokenization: Breaking down text into tokens (words, phrases).
• Named Entity Recognition (NER): Identifying entities such as names, organizations, and
locations.
• Sentiment Analysis: Determining the sentiment expressed in a piece of text (e.g., positive,
negative, neutral).
• Machine Translation: Translating text from one language to another.
Applications:
• Chatbots and Virtual Assistants: Enabling natural language interaction with machines.
• Text Summarization: Generating concise summaries of long texts.
• Language Translation: Facilitating communication across different languages.
Challenges:
 • Ambiguity: Natural language is often ambiguous and context-dependent.
• Sarcasm and Irony: Detecting and interpreting non-literal language.

3. Computer Vision (CV)

Definition:
Computer Vision is a subfield of AI that focuses on enabling computers to interpret and understand
visual information from the world, such as images and videos. The goal is to replicate the human
visual system’s ability to perceive and understand the environment.
Key Concepts:
• Image Processing: Techniques for enhancing and transforming images.
• Feature Extraction: Identifying and extracting important features from images.
• Object Recognition: Identifying and classifying objects within images.
• Scene Understanding: Interpreting the context and relationships within a scene.
Techniques:
• Convolutional Neural Networks (CNNs): A type of deep learning model particularly
effective for image-related tasks.
• Object Detection: Locating and classifying multiple objects within an image.
• Image Segmentation: Dividing an image into multiple segments to simplify analysis.
Applications:
• Autonomous Vehicles: Enabling cars to perceive and navigate their environment.
• Medical Imaging: Assisting in the diagnosis and treatment of diseases through image
analysis.
• Facial Recognition: Identifying and verifying individuals based on their facial features.
Challenges:
• Variability: Images can vary greatly due to lighting, angles, and occlusions.
• Scale and Rotation: Objects can appear at different scales and orientations.

4. Robotics
Definition:
Robotics is a subfield of AI that combines mechanical engineering, electrical engineering, and
computer science to design, construct, and operate robots. The goal is to create machines that can
perform tasks autonomously or semi-autonomously.
Key Concepts:
• Sensing: Using sensors to perceive the environment (e.g., cameras, lidar, sonar).
• Actuation: Controlling physical components to interact with the environment (e.g., motors,
actuators).
• Control Systems: Algorithms that manage the behavior of robots.
• Navigation and Mapping: Enabling robots to move through and understand their
environment.
Techniques:
 • Path Planning: Determining the optimal path for a robot to reach a destination.
• SLAM (Simultaneous Localization and Mapping): Creating a map of an unknown
environment while simultaneously keeping track of the robot's location.
• Reinforcement Learning in Robotics: Training robots to perform tasks through trial and
error.
Applications:
• Manufacturing: Robots used in assembly lines for tasks such as welding and painting.
• Healthcare: Surgical robots and robotic prosthetics.
• Service Robots: Robots that assist with tasks such as cleaning, delivery, and customer
service.
Challenges:
• Real-Time Processing: Responding to dynamic environments quickly and accurately.
• Safety and Reliability: Ensuring that robots operate safely and consistently.

III. AI Applications in Various Industries

Artificial Intelligence (AI) has permeated numerous industries, transforming processes, enhancing
efficiency, and enabling new possibilities. Below is an overview of how AI is applied across several
key sectors:

1. Healthcare
Applications:
• Medical Imaging and Diagnostics:
• Radiology: AI algorithms assist radiologists in detecting abnormalities in X-rays,
MRIs, and CT scans with high accuracy.
• Pathology: AI can analyze tissue samples to identify cancerous cells and other
pathologies.
• Predictive Analytics:
• AI models predict patient outcomes, such as the likelihood of readmission or the
progression of chronic diseases.
• Personalized Medicine:
• AI analyzes genetic information to tailor treatments to individual patients, optimizing
drug efficacy and minimizing side effects.
• Drug Discovery:
• AI accelerates the discovery of new drugs by analyzing vast datasets to identify
potential compounds and predict their effectiveness.
• Virtual Health Assistants:
• AI-powered chatbots and virtual nurses provide patients with medical information,
schedule appointments, and monitor health metrics.
Benefits:
• Improved diagnostic accuracy.
• Enhanced patient care and personalized treatment plans.
• Reduced costs and increased efficiency in healthcare delivery.
2. Finance
Applications:
• Fraud Detection:
• AI systems monitor transactions in real-time to identify and prevent fraudulent
activities.
• Algorithmic Trading:
• AI algorithms analyze market data to execute trades at optimal times, maximizing
returns.
• Risk Assessment:
• AI models assess creditworthiness and predict loan defaults, enabling more accurate
risk management.
• Customer Service:
• AI-powered chatbots and virtual assistants provide customer support, handling
inquiries and transactions.
• Portfolio Management:
• AI optimizes investment portfolios based on market trends and individual risk
profiles.
Benefits:
• Enhanced security and fraud prevention.
• Improved decision-making and resource allocation.
• Increased customer satisfaction through personalized services.

3. Retail and E-commerce

Applications:
• Recommendation Systems:
• AI analyzes customer behavior and preferences to suggest products, increasing sales
and customer engagement.
• Inventory Management:
• AI predicts demand and optimizes inventory levels, reducing waste and ensuring
product availability.
• Customer Service:
• AI chatbots handle customer inquiries, provide product information, and assist with
purchases.
• Visual Search:
• AI enables customers to search for products using images, enhancing the shopping
experience.
• Price Optimization:
• AI analyzes market trends and competitor pricing to set optimal prices for products.
Benefits:
• Improved customer experience and satisfaction.
• Increased sales and revenue through personalized recommendations.
• Enhanced operational efficiency and cost savings.
4. Manufacturing
Applications:
• Predictive Maintenance:
• AI monitors equipment performance and predicts failures, enabling timely
maintenance and reducing downtime.
• Quality Control:
• AI systems inspect products for defects, ensuring high quality and reducing waste.
• Supply Chain Optimization:
• AI analyzes supply chain data to optimize logistics, reduce costs, and improve
delivery times.
• Robotics and Automation:
• AI-powered robots perform tasks such as assembly, welding, and packaging,
increasing efficiency and precision.
Benefits:
• Increased productivity and efficiency.
• Reduced maintenance costs and downtime.
• Improved product quality and consistency.

5. Transportation and Logistics

Applications:
• Autonomous Vehicles:
• AI enables self-driving cars, trucks, and drones, transforming transportation and
logistics.
• Route Optimization:
• AI algorithms determine the most efficient routes for delivery vehicles, reducing fuel
consumption and delivery times.
• Demand Forecasting:
• AI predicts demand for transportation services, optimizing resource allocation and
pricing.
• Fleet Management:
• AI monitors vehicle performance and driver behavior, improving safety and
efficiency.
Benefits:
• Enhanced safety and reduced accidents.
• Improved efficiency and reduced costs.
• Increased sustainability through optimized resource usage.

6. Agriculture
Applications:
• Precision Agriculture:
• AI analyzes data from sensors, satellites, and drones to optimize farming practices,
such as irrigation, fertilization, and pest control.
 • Crop Monitoring:
• AI monitors crop health and predicts yields, enabling better planning and resource
management.
• Livestock Monitoring:
• AI tracks livestock behavior and health, improving animal welfare and productivity.
• Agricultural Robotics:
• AI-powered robots perform tasks such as planting, harvesting, and sorting, increasing
efficiency and reducing labor costs.
Benefits:
• Increased crop yields and reduced resource consumption.
• Improved animal health and welfare.
• Enhanced sustainability and environmental impact.

7. Entertainment and Media

Applications:
• Content Recommendation:
• AI analyzes user preferences and behavior to recommend movies, music, and other
content.
• Content Creation:
• AI generates music, art, and even written content, opening new creative possibilities.
• Virtual Reality (VR) and Augmented Reality (AR):
• AI enhances VR and AR experiences by creating immersive and interactive
environments.
• Video and Image Processing:
• AI improves the quality of videos and images, enabling features such as automatic
editing and enhancement.
Benefits:
• Enhanced user experience and engagement.
• New creative opportunities and innovations.
• Improved content delivery and personalization.