BAMU · Final Year B.E. Electronics & Telecommunication Engineering · CBCS (2019)
AI and ML
ETC442 · Elective I · Semester VII · 4 credits · CT 20 + theory 80
One of the Elective I options.
Unit 1: AI, Problem Spaces and Search; Intelligent Agents
8 hoursWhat AI is, its problems and techniques; problems as state-space search, production systems and their characteristics, issues in search programs; agents, environments and agent structure.
Examined in the 80-mark end-semester paper
- Artificial intelligence: definition and history
- Problem-solving agents and state-space search
- Production systems and problem characteristics
- Intelligent agents and their types
- Types of environments
Unit 2: Heuristic Search, Knowledge Representation, Predicate Logic and Logical Agents
6 hoursGenerate-and-test, hill climbing, best-first search, problem reduction, constraint satisfaction and means–ends analysis; knowledge-representation approaches and the frame problem; predicate logic, resolution and natural deduction; knowledge-based agents, the wumpus world and propositional theorem proving.
Examined in the 80-mark end-semester paper
- Hill climbing, beam and tabu search
- Best-first and greedy search
- Problem reduction and means–ends analysis
- Constraint satisfaction problems
- Knowledge representation issues and the frame problem
- Unification and resolution
- Knowledge-based agents and the wumpus world
- Propositional logic and theorem proving
Unit 3: Symbolic Reasoning under Uncertainty
4 hoursNonmonotonic reasoning and its logics, implementation issues, augmenting a problem solver, and depth-first and breadth-first implementations.
Examined in the 80-mark end-semester paper
- Nonmonotonic reasoning
- Uninformed search: BFS, DFS and uniform cost
Unit 4: Slot-and-Filler Structures; Adversarial Search
8 hoursSemantic nets and frames; conceptual dependency, scripts and CYC; games, optimal decisions, alpha–beta pruning, imperfect real-time decisions, stochastic and partially observable games.
Examined in the 80-mark end-semester paper
- Frames, semantic nets and conceptual dependency
- Scripts and CYC
- Minimax and alpha–beta pruning
- Stochastic and partially observable games
Unit 5: Learning I
6 hoursMachine learning's concept, scope, goals and challenges; generative, discriminative and imitative modelling; rote, observational, supervised, unsupervised, semi-supervised, ensemble and discovery-based learning; Bayesian networks and learning, and the EM algorithm.
Examined in the 80-mark end-semester paper
- Forms of learning in AI
- Generative and discriminative learning paradigms
- Supervised, unsupervised, semi-supervised and ensemble learning
- Bayesian networks and the EM algorithm
Unit 6: Learning II
8 hoursBackpropagation, support vector machines, reinforcement learning and Q-learning; multi-agent, distributed, adaptive, speed-up, analytical and active learning; prior knowledge, bias, noise and evaluation.
Examined in the 80-mark end-semester paper
- Backpropagation and support vector machines
- Reinforcement learning basics
- Q-learning
- Active, adaptive and distributed learning
Unit contents are summarised from the official BAMU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Marathwada University (BAMU).