CBCGS [2019 - current]

CBGS [2015 - 2018]

Old [2000 - 2014]

## University of Mumbai Semester 8 (BE Fourth Year) Artificial Intelligence Revised Syllabus

University of Mumbai Semester 8 (BE Fourth Year) Artificial Intelligence and their Unit wise marks distribution

### Units and Topics

## Syllabus

100 Module 1

101 Ai and Internal Representation

- Artificial Intelligence and the World, Representation in AI, Properties of Internal Representation, The
- Predicate Calculus Intelligent Agents: Concept of Rational Agent, Structure of Intelligent agents, Agent Environments.
- Problem Solving : Solving problems by searching, Problem Formulation, Search Strategies, Uninformed Search Techniques, DFS, BFS, Uniform cost search, Iterative Deepening, Comparing different Techniques, Informed search methods – Best First Search, heuristic functions, Hill Climbing, A*.IDA*. Crypt Arithmetic, Bactracking for CSP

200 Module 2

201 Programming in Lisp Or Prolog

- Lisps, Typing at Lisp,
- Defining Programs,
- Basic Flow of Control in Lisp,
- Lisp Style,
- Atoms and Lists,
- Basic Debugging,
- Building Up List Structure,
- More on Predicates,
- Properties, Pointers,
- Cell Notation and the Internals (Almost) of Lisp,
- Destructive Modification of Lists,
- The for Function,
- Recursion,
- Scope of Variables Input/Output, Macros

300 Module 3

301 Fundamentals Concepts and Models of Artificial Neural Systems

- Biological Neuron and their Artificial Models, Models of ANN, Learning and Adaptation, Neural Networking Learning Rules.
- Single-layer Perception Classifiers Multilayer Feed forward Networks : Linearly Nonseparable Pattern Classification, Delta Learning Rule, Feed forward Recall and Error BackPropagation Training, Learning Factor

400 Module 4

401 Fuzzy Systems

- Fuzzy Sets: Fuzzy Relations, Fuzzy Function, Fuzzy Measures, probabilities possibilities.
- Fuzzy Modeling and applications of Fuzzy Control. Neural and fuzzy machine Intelligence

500 Module 5

501 Generic Algorithm

- Simple generic algorithm,
- Simulation by hands,
- similarity templates (Schemata),
- Mathematical foundations,
- Schema processing at work,
- Two armed and k armed Bandit Problem,
- Building blocks hypothesis,
- Minimal Deceptive Problem,
- Computer implementation of generic algorithm,
- Data structures, Reproduction, Cross over and mutation.
- Time to response and time to cross mapping objective function to fitness from fitness scaling.
- Application of generic algorithm.
- De Jong and Function Optimization.
- Improvement in basic techniques, Improvement to genetics based machine learning, application of genetic based machine learning

600 Module 6

601 Data Mining and Information Retrieval

- Data warehousing & Data Mining.
- Online Analytic Processing [OLAP]: its architecture and its use.
- Java implementations, classification trees and exploratory data analysis [EDA].
- EDA Vs Hypothesis Testing, Computational EDA Techniques, Graphical [Data Visualization], EDA techniques for function fitting, data smoothing, layering, tessellations, contour projections, Verification of results of EDA. Applications & trends in data mining.
- Case Studies

Advertisement Remove all ads

Advertisement Remove all ads