This course provides a comprehensive introduction to Artificial Intelligence and its applications. It begins with fundamental AI concepts, history, types of AI, and intelligent agents. Students will explore problem-solving techniques through state-space search, both uninformed and informed, and gain insights into knowledge representation and reasoning under uncertainty. The course covers supervised and unsupervised machine learning methods, including regression, classification, clustering, and dimensionality reduction. Reinforcement learning and deep learning fundamentals are introduced, extending to practical applications in computer vision and natural language processing. The course concludes with discussions on AI ethics, societal impacts, safety concerns, and future trends, fostering responsible AI development.

SYLLABUS

 Module 1: Introduction to Artificial Intelligence

Definitions and History of AI, Goals and Applications of AI, Types of AI: Narrow AI, General AI, Super AI; AI Agents and Environments (PEAS).

Problem Solving with Search: Problem-solving agents, Formulating problems: State space search, search trees, Uninformed Search Strategies: Breadth-First Search, Depth-First Search, Depth-limited Search, UCS,  Informed Search Strategies: Greedy Best-First Search, A* Search, Knowledge Representation and Reasoning: Logical Agents: Propositional Logic, Predicate Logic (First-Order Logic), Syntax and Semantics of Propositional and First-Order Logic, Reasoning with Uncertainty.

 Module 2: Introduction to Supervised and Unsupervised Learning

Machine Learning definitions, Canonical Paradigms of ML, Supervised Learning: Regression: Linear Regression, Classification: k-Nearest Neighbors (k-NN), Decision Trees, Naive Bayes, Logistic Regression.

Unsupervised Learning: Clustering: k-Means Clustering, Hierarchical Clustering. Dimensionality Reduction: Principal Component Analysis (PCA)

 Module 3: Introduction to RL & DL

Introduction to Reinforcement Learning: Agents and Environments, Element of RLs, Real life examples of RL. Introduction to Deep Learning: Mathematical model of single neuron (McCulloch-Pitts model), Perceptrons, Activation Functions, Multilayered Feedforward Neural Networks, Conceptual introduction to Backpropagation in ANNs.

 Module 4: Deep Learning for Computer Vision

Overview of Computer Vision: Basic Image Processing Techniques.

Introduction to Convolutional Neural Networks. Application of CNNs - Image Classification, Object Detection,

 Module 5:

Deep Learning for NLP: Overview of NLP: Basic NLP techniques, Conceptual introduction to Deep Learning models for NLP applications.

AI Ethics and Future Trends: Ethical issues in AI, Societal Impact of AI, AI safety and Control, AI for Social Good.

Requirements

Knowledge of basic  Linear Algebra, Calculus, and Probability Theory

Course Staff

Staff 1