INTERNATIONAL BURCH UNIVERSITY
Graduate Study - Faculty of Engineering and Natural Sciences
Information Technologies Master (4+1) Without Thesis
2011-2012

SYLLABUS
Code Name Level Year Semester
CEN 591 Neural Networks Graduate 1 Spring
Status Number of ECTS Credits Class Hours Per Week Total Hours Per Semester Language
7.5 0 English

Instructor Assistant Coordinator
Günay Karli, Assoc. Prof. Dr. Abdülhamit Subaşı, Prof. Dr.
[email protected] no email

COURSE OBJECTIVE

COURSE CONTENT
Week
Topic
  1. Perceptrons: Simple and Multilayer, Perceptrons as Models of Vision De
  2. Linear Networks,Retina
  3. Lateral Inhibition and Feature Selectivity ,Objectives and Optimization
  4. Hybrid Analog-Digital Computation Ring Network , Constraint Satisfaction
  5. Stereopsis
  6. Bidirectional Perception
  7. Signal Reconstruction, Hamiltonian Dynamics
  8. Antisymmetric Networks ,Excitatory-Inhibitory Networks Learning
  9. Associative Memory , Models of Delay Activity
  10. Integrators, Multistability
  11. Clustering, VQ, PCA
  12. Delta Rule , Conditioning Backpropagation
  13. Stochastic Gradient Descent
  14. Reinforcement Learning

LABORATORY/PRACTICE PLAN
Week
Topic

    TEACHING/ASSESSMENT
    Description
    • Lectures
    • Project
    Description (%)
    Method Quantity Percentage (%)
    Homework110
    Project120
    Midterm Exam(s)120
    Final Exam140
    +participation
    10
    Total: 90
    Learning outcomes
    • Demonstrate a systematic and critical understanding of the theories, principles and practices of computing;
    • Critically review the role of a “professional computing practitioner” with particular regard to an understanding of legal and ethical issues;
    • Creatively apply contemporary theories, processes and tools in the development and evaluation of solutions to problems and product design;
    • Actively participate in, reflect upon, and take responsibility for, personal learning and development, within a framework of lifelong learning and continued professional development;
    • Present issues and solutions in appropriate form to communicate effectively with peers and clients from specialist and non-specialist backgrounds;
    TEXTBOOK(S)
    • Hertz, John, Anders Krogh, and Richard G. Palmer. Introduction to the Theory of Neural Computation. Redwood City, CA: Addison-Wesley Pub. Co., 1991. ISBN: 9780201515602.
    • Koch, Christof. Biophysics of Computation: Information Processing in Single Neurons. New York, NY: Oxford University Press, 2004, ISBN: 9780195181999

    ECTS (Allocated based on student) WORKLOAD
    Activities Quantity Duration (Hour) Total Work Load
    Lecture (14 weeks x Lecture hours per week) 0
    Laboratory / Practice (14 weeks x Laboratory/Practice hours per week) 0
    Midterm Examination (1 week) 0
    Final Examination(1 week) 0
    Preparation for Midterm Examination 0
    Preparation for Final Examination7.50
    Total Workload: 0
    ECTS Credit (Total workload/25): 0