Lecture-wise Topics to be covered
Name of Lecture Topics to be covered
Lecture 1 Evolution of Computing, Intelligent machines, or what machines can do. The
Turing Imitation Game, Applications of AI Techniques (Just brief discussion with
graphical illustration if possible).
Expert Systems
Image Understanding and Computer Vision
Navigational Planning for Mobile Robots
Speech and Natural Language Understanding
Scheduling
Intelligent Control
Lecture 2 A Brief History of AI
The Classical Period
The Romantic Period
The Modern Period
Give a glimpse of several Disciplines of AI
Learning Systems
Knowledge Representation and Reasoning
Planning
Knowledge Acquisition
Intelligent Search
Logic Programming
Soft Computing
Fuzzy Logic
Artificial Neural Nets
Genetic Algorithms
Management of Imprecision and Uncertainty
THE STATE OF THE ART and Programming Language of AI.
Lecture 3 Introduction to Intelligent Agents with its Environments. Demonstration with A
vacuum-cleaner world. The rational agent and task environment with PEAS
description. Examples of Agent types and their PEAS description. [Just give an
idea about intelligent agent].
Lecture 4 Introduction to State Space Representation. Identify the AI problems and
Problem Formulation by Search. Search Framework.
Lecture 5 Illustrating examples on AI problem formulation such as Missionary and
Cannibal problems, Water Jug Problems, Tower of Hanoi, Monkey and
Banana, 8 Queens Problems and 8 Puzzle Problems.
Lecture 6 Basic Search Algorithm Framework. Breadth First Search Concepts and
illustration with examples
Lecture 7 Depth First Search Concepts and illustration with examples
Lecture 8 Introduction to Supervised, Unsupervised and Reinforcement Learning.
Explain with graphical illustrations and real-life examples.
Lecture 9 Performance Evaluation Metrics (Accuracy, Precision, Recall, F1-Score,
ROC etc.) of supervised classification techniques
Lecture 10 Performance Evaluation Metrics (Accuracy, Precision, Recall, F1-Score,
ROC etc.) of supervised classification techniques.
Lecture 11 Introduction to Cross-validation method and its usage.
Lecture 12 Introduction to Probability Density Function and Conditional probability to
understand Bayes’ classifier.
Lecture 13 Mathematical Formulation of Bayes’ Decision Rule
Lecture 14 Different Case studies of Bayes’ Decision Rule
Lecture 15 Single Variate regression Analysis
Lecture 16 Multi-variate regression analysis
Lecture 17 Introduction to Logistic Regression
Lecture 18 Single Layer Perceptron Algorithm
Lecture 19 Multi-Layer Perceptron Algorithm (Backpropagation method)
Lecture 20 Solving numerical problems on Single and Multi-layer perceptron
algorithms
Lecture 21 K-Nearest Neighbour Algorithm
Lecture 22 Introduction to Clustering and its properties
Lecture 23 K-Means clustering algorithm
Lecture 24 Introduction to DBSCAN clustering algorithm
Lecture 25 Examples on K-Means and DBSCAN clustering algorithms.
Lecture 26 Concepts of Dendrogram and Cluster validity with numerical
examples
