[PDF] Artificial Intelligence (AI) - 6th Semester Notes & Syllabus | Diploma in Computer Engineering/IT

  Here, The Course Note and syllabus of Artificial Intelligence(AI) at the 6th semester of Diploma in Computer Engineering/IT CTEVT.

[PDF] Artificial Intelligence (AI) - 6th Semester Notes & Syllabus | Diploma in Computer Engineering/IT

The Course Note of Artificial Intelligence is in PDF format.

Complete Notes: 

The Syllabus of Artificial Intelligence at 1st Semester:

[PDF] Artificial Intelligence (AI) - 6th Semester Notes & Syllabus | Diploma in Computer Engineering/IT

Artificial Intelligence

EG 3203 CT

                                                                                                    Total: 8 hours /week

Year: III                                                                                       Lecture: 4 hours/week

Semester: II                                                                                Tutorial: 1 hour/week

                                                                                                    Practical: 3 hours/week

Course Contents:

Unit 1. Goals in problem-solving:                 [7]

Goal schemas, use in planning, Concept of non-linear planning, Means–end analysis, Production rules systems, forward and backward chaining, Mycin-style probabilities and its application

Unit 2. Intelligence:               [6]

Introduction of intelligence, Modeling, humans vs. engineering performance, representing intelligence using and acquiring knowledge

Unit 3. Knowledge Representation:               [7]

Logic, Semantic networks, Predicate calculus, Frames

Unit 4. Inference and Reasoning:               [10]

Inference, theorems, Deduction and truth, maintenance, Heuristic search, State- space representations, game playing. Reasoning about uncertainty Probability, Bayesian networks, Case-based Reasoning

Unit 5. Machine Learning:                 [10]

Concepts of learning (based on Winston), Learning by analogy, Inductive bias learning, Neural networks, Genetic algorithms, Explanation based learning, Boltzmann Machines

Unit 6. Application of artificial intelligence:                 [20]

Neural networks: Network Structure, Adaline, Madaline, Perceptron, Multi-layer Perceptron, Radial Basis Function, Hopfield network, Kohonen Network, Elastic net model, back-propagation

Expert Systems: Architecture of an expert system, Knowledge acquisition, induction, Knowledge representation, Declarative knowledge, Procedural knowledge, Knowledge elicitation techniques, Intelligent editing programs, Development of expert systems

Natural language Processing: Levels of analysis: Phonetic, syntactic, semantic, pragmatic, Machine Vision: The bottom-up approach, edge extraction, line detection, line labeling, shape recognition, image interpretation, need for top-down, hypothesis-driven approaches.

Practical:                                                                                     [45]

1.     Laboratory exercises should cover the design and development of artificial intelligence using the LISP and Prolog software.

2. Laboratory exercises must be designed to develop Search, Inference including forward and backward chaining in Object-Oriented Language, Design and implementation of Artificial Neural Networks.