ARTIFICIAL INTELLIGENCE: PRINCIPLES, TECHNIQUES, AND APPLICATIONS

This course introduces the fundamental concepts and techniques in Artificial Intelligence (AI), emphasizing the development of intelligent agents that can perceive, reason, learn, and act. Covering both theoretical foundations and practical applications, it includes areas such as search strategies, knowledge representation, machine learning, deep learning, natural language processing, and computer vision. The course also addresses ethical implications of AI, preparing students for responsible use of intelligent systems in real-world scenarios.

COURSE DURATION

One Semester (15 Weeks)

PREREQUISITES

Basic programming (preferably Python)

Knowledge of mathematics: Linear Algebra, Probability, Calculus

Intro to Data Structures and Algorithms (recommended)

COURSE OBJECTIVES

Students will:

1. Learn basic AI principles, concepts, and terminology.

2. Understand and apply problem-solving and search techniques.

3. Explore machine learning algorithms and training methods.

4. Work with natural language and visual data.

5. Examine AI’s role in society, ethics, and decision-making.

LEARNING OUTCOMES

Upon completion, students will be able to:

Develop simple intelligent agents and search-based problem solvers.

Apply supervised and unsupervised learning models.

Analyze and preprocess data for AI tasks.

Build basic models for NLP and computer vision.

Discuss ethical issues in deploying AI systems.

COURSE OUTLINE / MODULES

Module 1: Introduction to AI

Definition and scope of AI

History and evolution

Applications of AI

AI vs. Human Intelligence

Module 2: Intelligent Agents

Agent types and environments

PEAS framework

Agent architecture

Module 3: Search Algorithms

Problem formulation

Uninformed search: BFS, DFS

Informed search: A*, Greedy

Game playing: Minimax, Alpha-Beta pruning

Module 4: Knowledge Representation and Reasoning

Propositional and predicate logic

Semantic networks

Inference rules

Expert systems

Module 5: Machine Learning

Supervised learning: Linear regression, Decision trees, SVMs

Unsupervised learning: Clustering, PCA

Model evaluation and tuning

Tools: Scikit-learn, Pandas

Module 6: Deep Learning

 Neural networks: Perceptron, Backpropagation

CNNs for images

RNNs for sequences

Frameworks: TensorFlow, PyTorch

Module 7: Natural Language Processing (NLP)

Tokenization, stemming, lemmatization

Bag-of-Words and word embeddings

Sentiment analysis

Transformer models (BERT, GPT – overview)

Module 8: Computer Vision

Image processing basics

Feature extraction

Object detection and classification

Applications in facial recognition, autonomous vehicles

Module 9: Robotics and Planning (Optional Advanced)

Motion planning

Perception and localization

Autonomous agents

Module 10: Ethics in AI

Bias and fairness

AI and employment

Explainability

Legal and social issues

ASSESSMENT STRUCTURE

Component                     Weight 

Assignments (Coding + Theory)  25%    

Midterm Exam                   20%    

Final Exam                      25%    

Project (Group or Individual)  20%    

Participation/Quizzes           10%   

TEXTBOOKS & REFERENCES

Primary Textbook:

Artificial Intelligence: A Modern Approach by Russell & Norvig

ADDITIONAL RESOURCES

Python Machine Learning by Sebastian Raschka

Deep Learning by Goodfellow, Bengio & Courville

Lecture notes, Jupyter notebooks, and online resources (Google Colab, Kaggle)

SOFTWARE TOOLS

Python

Jupyter Notebook

scikit-learn

TensorFlow / PyTorch

OpenCV

NLTK / spaCy