Introduction of Smart System Design and Application

(BE Computer 2012 Pattern SEM-I)

Course Relevance:-

The Goal for this course/subject is introduce you to the field of Artificial Intelligence.Explain to you the challenges that are inherent in building a system that can be considered to be intelligent. This subject mainly focused on the area of Artificial Intelligence and its application. It gives the fundamental knowledge about the different algorithm which helps you to design smart system and its application in distributed, concurrent and parallel environments.Since the invention of computers or machines, their capability to perform various tasks went on growing exponentially. Humans have developed the power of computer systems in terms of their diverse working domains, their increasing speed, and reducing size with respect to time.Abranch of Computer Science named Artificial Intelligence pursues creating the computers or machines as intelligent as human beings.

This Subject Divided into 6 Different parts:-

  1. First Part Covers the Introduction to the Intelligent System,History, Foundations and Mathematical treatments, Problem solving with AI, AI models, Learning aspects in AI, What is an intelligent Agents, Rational agent, Environments types, types of Agents.
  2. Second part of the Subject covers Problem-solving and Building Smart Systems, On taking this course you should be able to formulate certain types of problems as state space search problems and you should learn the efficient methods to solve them depending upon the characteristics of the problem space , you should be able to write programs that play games particularly two player games , you should be able to use learning to find patterns in data to find rules from data , you should be able to build expert systems for different diagnostic and other purposes . Problem solving process,Problem analysis and representation, Problem space and search, Toy problems, real world problems, Problem reduction methods, general search problem Informed Search, uninformed Search state space search. Best first, Greedy, A* search methods, Heuristic Functions, AO*, Local Search Algorithms and optimization problems, Adversarial search methods, Important concepts of Game theory, Game theory and knowledge structure, Game as a search problem, Alpha-Beta Pruning, Stochastic Games, Constraint Satisfaction Problem, CSP as search problem
  3. Third Part of Subject Covers Knowledge, Reasoning, and Planning, Knowledge based agents, The Wumpus World, Logic, propositional logic, Representation of knowledge using rules, Predicate logic, Unification and lifting, inference in FOL, Forward Chaining, Backward Chaining, Resolution, Logic Programming. Planning problem, Planning, Algorithms for Planning as State-Space Search, Planning Graphs, simple planning agent, planning languages, blocks world problem, goal stack planning, mean end analysis, progression planners, regression planners, partial order planning, planning graphs, hierarchical planning, job shop scheduling problem, Planning and Acting in the Real World, Hierarchical Planning, Multi-agent Planning, Ontological Engineering, Categories and Objects, Events, Mental Events and Mental Objects, Reasoning Systems for Categories, Reasoning with Default Information,The Internet Shopping World.
  4. Fourth Part of Subject Covers Uncertain Knowledge and Decision Theory , Uncertainty and methods, Basic Probability Notion, Inference Using Full Joint Distributions, Bayesian probability and belief networks, Relational and First Order Probability Models, Other techniques in uncertainty and reasoning, Inference in Temporal Models, Hidden Markov Models, Kalman Filters, Dynamic Bayesian Networks, Decision network, Semi-constraint influence diagram, Decision making and imperfect information, Combining Beliefs and Desires under Uncertainty, The Basis of Utility Theory, Utility Functions, Multi-attribute Utility Functions, Decision Networks, Decision-Theoretic Expert Systems
  5. Fifth part of Subject Covers Learning Tools, Techniques and Applications Machine Learning Concepts, methods and models, Supervised Learning, unsupervised and semi-supervised, Learning Decision Trees, Evaluating and Choosing the Best Hypothesis, Artificial Neural Networks, Non-parametric Models, Support Vector Machines, Ensemble Learning, empirical learning tasks, Explanation-Based Learning, Inductive Logic Programming, Reinforcement Learning, Active Learning, Learning based on limited information. Building Smart systems using different learning techniques, smart system applications, agent based concurrent engineering.
  6. Six Part of Subject Covers Communicating, Perceiving, and Acting Language Models, Text Classification, Information Retrieval, Information Extraction, Phrase Structure Grammars, Syntactic Analysis (Parsing), Augmented Grammars and Semantic Interpretation, Machine Translation, Speech Recognition, Image Formation and object recognition, Early Image-Processing Operations, Object Recognition by Appearance, Reconstructing the 3D World, Object Recognition from Structural Information, Using Vision, Robot Hardware, Robotic Perception, Planning to Move,Planning Uncertain Movements, Robotic Software Architectures, Application Domains.

This Subject is Mostly covers all the part of Artificial Intelligent Course so lot of NPTEL videos of the course which is available free of charge on

NPTEL Link Available to access Subject Notes:-

Pre-requisites of the subject/course:-

  1. Knowledge of wide variety of artificial intelligence problems like real world problem.
  2. Knowledge of wide variety of artificial intelligence search problems and its method.
  3. Knowledge of FOL ie First order logic and logical programming and various rule of knowledge representation.
  4. Knowledge of Basic Probability Notion, Uncertainty and methods, basics of Utility theory and Decision-Theoretic Expert Systems.
  5. Knowledge of Machine Learning , Types of Learning and different learning technique and tools.
  6. Knowledge of Information Retrieval, Extraction and Object Recognisation and ROBOT Hardware, Software and Perception.

Course Objective:-

  1. To study multidisciplinary requirements of problem solving.
  2. To study concepts of Artificial Intelligence.
  3. To study smart systems programming and application development.
  4. To study examples in distributed, concurrent and parallel environments.

Course Outcomes:-

  1. The study of one solve multidisciplinary case-study.
  2. To use embedded systems using machine learning.
  3. To solve problems for multi-core or distributed, concurrent and embedded environments.
  4. The students will incrementally build intelligent agents with (i) problem solving, (ii) reasoning and (iii) learning capabilities through a thread case study.

Experts Related to Subject:-

  1. Dr. Parag Kulkarni is one of the world’s leading authorities on Business Strategy, Knowledge Innovation, Machine Learning, Systemic Learning and Building Innovative Knowledge Corporations in the knowledge economy.

Research: Dr. Parag published more than 200 research papers. Some of them are listed at:

Web Site: - www.drparagkulkarni.com

Industries Related to Subject:-

  1. EkLaT Research , Pune
  2. Google
  3. Wipro Technology , Pune
  4. Flipkart

Career opportunities or Linkage of thesubject/course in industry:-

  1. Game programmer.
  2. Face Recognition
  3. Google hire the People who manage Massive Search Engine ie Search Engine Optimization.
  4. ROBOT Development like Programming, simulation, circuit design, hardware manufacturing.
  5. Algorithm development for Smart Homes, smart device.

Weightage of the course in GATE Exam, Previous GATE Q-paper discussion in such forum