IE502515 Big Data

Course level

  • Second cycle

Credits

  • 7,50

Duration (semesters)

  • 1 semester

Teaching language

  • English

Prerequisites

  • Data structures
  • Computer programming – both Object-Oriented Programming and Procedural Programming
  • Algorithm design and analysis
  • Distributed programming (IE501513)
  • Statistics and probabilities

Topic list
1. Introduction to Big Data Analytics (BDA)

  • What is BDA?
  • Why BDA?
  • Data Mining and Machine Learning

Theme 1 will establish a fundamental understanding of BDA for the discussions in later themes.

2. CPU architectures for BDA

  • Data input
  • Basic algorithms
  • Knowledge presentation

Theme 2 will discuss on BDA techniques using CPU architectures.

3. GPU/FPGA architectures for BDA

  • Introduction to GPU and FPGA programming
  • CUDA and OpenCL
  • BDA using GPU or FPGA

Theme 3 will discuss on BDA techniques using GPU/FPGA architectures.

4. Implementation of BDA applications

Theme 4 will include practical exercises and projects in BDA techniques using CPU or GPU or FPGA architectures.

Teaching Methods

  • Lectures, exercises, obligatory project assignments.

Learning outcome – Knowledge

  • Have knowledge in the principles and challenges in the design and development of BDA technology
  • Have knowledge in the advantages of different architectures regarding BDA applications

Learning outcome – Skills

  • Be able to apply appropriate techniques in different BDA problems

Learning outcome – General competence

  • Be able to discuss and communicate the possibilities and limitations in the field of BDA

Mandatory Assignments

  • All obligatory project assignments must be graded D or better in order to get access to the exam.

Evaluation

  • Oral exam
  • Semester assignment, semester paper, project assignment and similar

Evaluation

  • Based on the student’s mastering of topics covered in lectures, and a demostration of mandatory (individual) exercises/projects.

Grading

  • Grading A-F. Grade F is a fail