RTMNU · Second Year B.Tech Artificial Intelligence & Machine Learning · NEP 2020
Artificial Intelligence
BAM3T09 · Semester III · 3 credits · College 30 + university 70
Unit 1: Introduction
6 hoursWhat AI is, its history and applications; AI as representation and search; production systems; problem representation paradigms and defining a problem as a state space.
Examined in the 70-mark end-semester paper
- What AI is and its history
- Applications of AI
- Rule-based systems and production rules
- State space representation
- Problem-solving agents
Unit 2: Search Techniques
7 hoursUninformed and informed heuristic search, generate and test, hill climbing, best-first search, problem reduction and constraint satisfaction.
Examined in the 70-mark end-semester paper
- Uninformed search: BFS, DFS and uniform cost
- Informed search: greedy and A*
- Heuristic functions
- Local search: hill climbing and simulated annealing
- Problem reduction and AND-OR graphs
- Constraint satisfaction problems
Unit 3: Knowledge Representation
8 hoursIssues in knowledge representation; first-order and predicate logic; forward and backward chaining and resolution; semantic nets, frames, scripts and ontologies.
Examined in the 70-mark end-semester paper
- Approaches to knowledge representation
- First-order logic
- Forward and backward chaining
- Resolution
- Semantic networks and frames
- Conceptual dependency and scripts
- Ontologies
Unit 4: Uncertainty and Intelligent Agents
8 hoursHandling uncertain knowledge and rational decisions, probability axioms, Bayes' rule and conditional independence, Bayesian networks with exact and approximate inference, and fuzzy logic; rational agents, their structure (reflex, model-based, goal-based and utility-based) and environments.
Examined in the 70-mark end-semester paper
- Total probability and Bayes' theorem
- Bayesian networks
- Exact and approximate inference in Bayesian networks
- Fuzzy sets and fuzzy logic
- Intelligent agents and environments
- Structure of agents
Unit 5: Learning and Expert Systems
7 hoursKnowledge and learning, learning in problem solving, learning from examples and learning probabilistic models; the building blocks of expert systems, knowledge engineering and acquisition, knowledge-based systems, and a basic understanding of natural language.
Examined in the 70-mark end-semester paper
- Learning from observation and inductive learning
- Types of machine learning
- Expert systems and knowledge engineering
Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).