BIT · Semester IV
Artificial Intelligence syllabus
Official TU syllabus for Artificial Intelligence (BIT252): 10 units, 61 topics. Every unit links to its notes and solved questions.
1
Foundations of Artificial Intelligence
9 Q- Definition and scope of artificial intelligence
- Turing test and machine intelligence
- Intelligent agents and rational agents
- PEAS framework for agent description
- Agent types and architectures
- Applications of artificial intelligence
2
Agent Environments and Problem Formulation
3 Q- Environment types and properties
- Deterministic and non-deterministic environments
- State space representation
- Goal formulation and problem definition
- Heuristic functions and evaluation metrics
3
Search Algorithms and Techniques
10 Q- Depth first search
- Breadth first search
- Depth limited search
- Iterative deepening search
- Hill climbing search
- Greedy best first search
- A* search algorithm
- AO* search for multiple goals
- Alpha beta pruning in game trees
- Search algorithm evaluation factors
4
Knowledge Representation
11 Q- Knowledge definition and representation issues
- Semantic networks
- Scripts and conceptual dependency
- First order predicate logic
- Clausal normal form conversion
- Unification and lifting in predicate logic
5
Reasoning and Inference
3 Q- Rules of inference
- Forward chaining
- Backward chaining
- Resolution method
- Constraint satisfaction problems
- Game theory and minimax algorithm
6
Uncertainty and Probabilistic Reasoning
3 Q- Dempster-Shafer theory
- Belief networks
- Statistical reasoning
- Certainty factors and reasoning
7
Expert Systems
5 Q- Expert system definition and purpose
- Expert system architecture
- Components of expert systems
- Development of expert systems
- Expert system operation and inference
8
Machine Learning and Neural Networks
7 Q- Machine learning definition
- Artificial neural network mathematical model
- Neuron structure and activation functions
- Feed-forward neural networks
- Recurrent neural networks
- Back-propagation algorithm
- Learning rules and learning rates
- Neural network types and architectures
9
Evolutionary and Reinforcement Learning
5 Q- Genetic algorithm operators
- Genetic algorithm learning process
- Reinforcement learning
- Rewards and punishment in learning
- Learning by analogy
10
Natural Language Processing
4 Q- NLP steps and pipeline
- Ambiguities in natural language
- Natural language understanding
- Natural language generation
- Discourse analysis
- Pragmatic analysis
Study BIT252 the smart way
Solved questions, flashcards & practice