Department of Computer Science and Engineering

B.Tech. III (CO) Semester - 5

L

T

P

C

CO305 : ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING(CS-3)

3

1

2

5
COURSE OBJECTIVES
  • To introduce the basic concepts, theories and state-of-the-art techniques of artificial intelligence.
  • To introduce basic concepts and applications of machine learning.
  • Help students to learn the application of machine learning /A.I algorithms in the different fields of science, medicine, finance etc.
    		•
    COURSE OUTCOMES
    After successful completion of this course, student will be able to
    • Understand concept of knowledge representation and predicate logic and transform the real life information in different representation.
    • Understand state space and its searching strategies.
    • Understand machine learning concepts and range of problems that can be handled by machine learning.
    • Apply the machine learning concepts in real life problems.
    COURSE CONTENT
    INTRODUCTION TO ARTIFICAL INTELLIGENCE

    (02 Hours)

    Foundation of AI, Example and Application.

    BASIC PROBLEM SOLVING METHODS

    (02 Hours)
    STATE SPACE SEARCH

    (04 Hours)

    Exhaustive search -BFS, DFS, Bidirectional Search,

    Heurisitc search - Hill Climbing, Beam Searchm Best First, A* search algorithm.

    LOGIC CONCEPT AND LOGIC PROGRAMMING

    (04 Hours)

    Propositional Logic, Predicate Logic

    KNOWLEDGE REPRESENTATION

    (04 Hours)

    Relational knowledge, Knowledge representation as logic, Semantic Network, Frame based knowledge.

    GAME THEORY

    (03 Hours)

    Look Ahead Strategy, Min-Max Approach, Alpha-Beta Pruning.

    FUZZY SETS AND FUZZY LOGIC

    (04 Hours)

    Fuzzy set operations, Membership functions, Fuzzy logic, Hedges, Fuzzy proposition and Inference rules, Fuzzy systems.

    PLANNING AND OPTIMIZATION

    (02 Hours)
    INTRODUCTION TO MACHINE LEARNING SYSTEMS

    (01 Hours)
    SUPERVISED LEARNING

    (06 Hours)

    General notions - Bayes optimality, curse of dimensionality, overfitting and model ,selection, bias vs. variance tradeoff, generative vs. discriminative for parameter estimation, feature selection, and etc Linear methods - linear, logistic regression and generalized linear models, naive Bayes, linear discriminant analysis, support vector machines, and etc.

    Nonlinear methods - kernel methods, nearest neighbor, decision trees, neural networks, and etc Ensemble learning - bagging, boosting, and etc.

    UNSUPERVISED LEARNING

    (04 Hours)

    Clustering and density estimations - K-means/vector quantization, mixture models, etc

    Dimensionality reduction - linear and nonlinear methods.

    PCA-Principal components analysis.

    ICA - Independent components analysis

    DEDUCTIVE LEARNING

    (04 Hours)

    Probability theory and Bayes rule. Naive Bayes learning algorithm. Parameter smoothing. Generative vs. discriminative training. Logisitic regression. Bayes nets and Markov nets for representing dependencies.

    ARTIFICIAL NEURAL NETWORKS

    (02 Hours)

    Neurons and biological motivation. Linear threshold units. Perceptrons: representational limitation and gradient descent training. Multilayer networks and backpropagation. Hidden layers and constructing intermediate, distributed representations. Overfitting, learning network structure, recurrent networks.

    (Total Contact Time: 42 Hours + 14 Hours = 56 Hours)
    BOOKS RECOMMENDED
    1. Elaine Rich, K. Knight, "Artificial Intelligence", 2/E, TMH, 1991.
    2. Andrew C., Staugaard Jr., Robotics and AI : "An Introduction to Applied Machine Intelligence", Prentice Hall ,1987 .
    3. S. Russell and P. Norvig, "Artificial Intelligence: A Modern Approach", 2/E, Prentice Hall, 2003.
    4. K. Boyer, L. Stark, H. Bunke, "Applications of AI, Machine Vision and Robotics" World Scientific Pub Co. , 1995.
    5. I. Bratko, "Prolog Programming for Artificial Intelligence", 3/E, Addison-Wesley, 2001.
    6. C. M. Bishop, "Pattern Recognition and Machine Learning", Springer, 2003.