Syllabus Artificial Intelligence - (BE05000151) Total Credits Assessment Pattern and Marks Total Marks Theory Tutorial / Practical ESE (E) PA/CA (M) PA/CA (I) PBL (I) ESE (V) 03 70 30 20 30 50 200 Unit No. Content 1. Introduction : The AI Problems, The Underlying Assumption, AI techniques, The Level of The Model, Criteria For Success. (Chapter - 1) 2. Problems, State Space Search & Heuristic Search Techniques : Defining The Problems As A State Space Search, Production Systems, Production Characteristics, Production System Characteristics and Issues in the Design of Search Programs, Generate-And-Test, Hill Climbing, Best-First Search, Problem Reduction, Constraint Satisfaction, Means-Ends Analysis. (Chapters - 2, 3) 3. Knowledge Representation : Representations And Mappings, Approaches To Knowledge Representation, Representation Simple Facts In Logic, Representing Instance And Isa Relationships, Computable Functions and Predicates, Resolution, Procedural versus Declarative Knowledge, Logic Programming, Forward versus Backward Reasoning. (Chapters - 4, 5, 6) 4. Symbolic Reasoning Under Uncertainty : Introduction To Nonmonotonic Reasoning, Logics For Non-monotonic Reasoning. (Chapter - 7) 5. Probabilistic Reasoning : Probability And Baye’s Theorem, Certainty Factors And Rule-Base Systems, Bayesian Networks, Dempster-Shafer Theory, Fuzzy Logic. (Chapter - 8) 6. Game Playing : Overview, MiniMax Search Procedure, Alpha-Beta Cut-offs, Refinements, Iterative deepening. (Chapter - 9) 7. Planning : The Blocks World, Components Of a Planning System, Goal Stack Planning, Nonlinear Planning Using Constraint Posting, Hierarchical Planning, Reactive Systems. (Chapter - 10) 8. Natural Language & Language Models : Introduction to NLP : Basics of Natural Language Processing, Tokenization, stemming, lemmatization, Word embeddings. Evolution of Language Models : Statistical language models (n-grams), RNNs, LSTMs, and their limitations Transition to attention-based models. Transformer Architecture : Encoder-decoder structure, Self-attention mechanism, Positional encoding, multi-head attention and feed-forward layers. Large Language Models : Pre-training, Fine-tuning and transfer learning, Prompt engineering basics, Applications : chatbots, summarization, translation. Challenges & Ethics : Bias, fairness, and hallucination in LLMs, Energy consumption and scalability, Alignment and safety concerns. (Chapter - 11) 9. Introduction to Prolog : Introduction, Converting English to Prolog Facts and Rules, Goals, Prolog Terminology, Variables, Control Structures, Arithmetic Operators, Matching in Prolog, Backtracking, Cuts, Recursion, Lists. (Chapter - 12)
