SUK · Third Year B.Tech. Computer Science and Engineering (Artificial Intelligence and Data Science) · NEP 2020
Artificial Intelligence
AI&DS3101 · Semester V · 3 credits · ISE 10 + mid-semester 30 + ESE 60
Unit 1: Logical Foundations of Artificial Intelligence
6 hoursSyntax and semantics of propositional logic; first-order predicate logic; knowledge representation using logic; logical inference, resolution and unification; forward and backward chaining.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Propositional logic and theorem proving
- First-order logic
- Inference and entailment
- Unification
- Resolution
- Forward and backward chaining
Unit 2: Knowledge Representation
6 hoursKnowledge-based agents; declarative knowledge; rule-based representation; semantic networks and frames; ontologies and knowledge graphs.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Knowledge-based agents and the wumpus world
- Procedural and declarative knowledge
- Rule-based systems and production rules
- Semantic networks and frames
- Ontologies
- Knowledge graphs: RDF, RDFS and OWL
Unit 3: Reasoning Under Uncertainty
6 hoursProbability basics and probabilistic reasoning; Bayesian networks, conditional independence and inference; decision making under uncertainty.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Probability and Bayes' theorem
- Bayesian networks
- Exact and approximate inference in Bayesian networks
- Hierarchical planning and planning under uncertainty
Unit 4: Machine Learning: Basic Concepts
6 hoursLearning agents; supervised and unsupervised learning; learning decision trees; regression models; model evaluation and validation.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Types of machine learning
- Learning from observation and inductive learning
- Decision tree learning and overfitting
- Simple and multiple linear regression
- Cross-validation and model evaluation
Unit 5: Neural Networks
6 hoursBiological versus artificial neurons; the perceptron; multilayer networks and the back-propagation algorithm; an overview of deep learning.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Biological and artificial neurons
- Perceptron learning rule
- Multilayer perceptron
- Backpropagation
- Feed-forward network architectures
Unit 6: Ethics and Future Directions of AI
6 hoursEthical issues, bias and fairness; transparency and explainability; safety and security of AI systems; social impact; future challenges and opportunities.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Bias in datasets and algorithms
- Algorithmic discrimination and fairness
- Explainable AI
- Job displacement and economic impact of AI
- AI governance, regulation and policy
Unit contents are summarised from the official SUK syllabus . AiCanCode.org is not affiliated with Shivaji University, Kolhapur.