SUK · Third Year B.Tech. Computer Science and Engineering (Data Science) · NEP 2020
Artificial Intelligence
DS3101 · Semester V · 3 credits · ISE 10 + mid-semester 30 + ESE 60
Unit 1: Artificial Intelligence and Its Issues
6 hoursDefinitions, importance, evolution and applications of AI; classification of AI systems by environment; knowledge-inferring systems and planning; uncertainty and learning systems.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- What AI is and its history
- Applications of AI
- Intelligent agents and environments
- Classical planning
Unit 2: Problem Solving and Heuristic Search
7 hoursProblem solving by search, problem and state spaces, blind search and its types, performance measures; game playing with minimax and alpha-beta pruning.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- State space representation
- Uninformed search: BFS, DFS and uniform cost
- Heuristic functions
- Minimax and optimal decisions in games
- Alpha-beta pruning
Unit 3: Probabilistic Reasoning and Markov Decision Processes
8 hoursProbability, conditional probability and Bayes' rule; Bayesian networks: representation, construction and inference; temporal models and hidden Markov models; MDP formulation, utility theory, value and policy iteration, partially observable MDPs.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Bayesian networks
- Exact and approximate inference in Bayesian networks
- Hidden Markov models
- Markov decision processes
- Value iteration
- Policy iteration
- Partially observable MDPs
Unit 4: Learning Systems and Expert Systems
7 hoursForms of learning: supervised, unsupervised and reinforcement; learning decision trees; expert systems: development stages, probability-based expert systems, tools, difficulties and applications.
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
- Expert systems and knowledge engineering
Unit 5: Reinforcement Learning
7 hoursPassive reinforcement learning, direct utility estimation, adaptive dynamic programming, temporal-difference learning; active reinforcement learning and Q-learning.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Monte Carlo prediction
- Dynamic programming for MDPs
- Temporal difference learning
- Q-learning
Unit 6: AI with Python
7 hoursPython libraries for AI (NumPy, SciPy, matplotlib, nltk, SimpleAI); installing and running Python; real-time AI applications; AI platforms: Azure ML, Google AI, Swift AI and TensorFlow.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Installing Python and running programs
- NumPy arrays and broadcasting
- Matplotlib and Seaborn
Unit contents are summarised from the official SUK syllabus . AiCanCode.org is not affiliated with Shivaji University, Kolhapur.