ICOM 4998: Undergraduate Researh - Fall 2013

Parallel Computing for Big Data Analytics


Dr. Wilson Rivera
Email: wrivera@ece.uprm.edu
Office Hours: Th; 9:00am-10:30am; S-411 
Lecture Hours: TBD

Course Information

Physical and economic limitations have forced computer architecture towards parallelism and away from exponential frequency scaling. Meanwhile, increased access to ubiquitous sensing and the web has resulted in an explosion in the data sets and it appears to be growing substantially faster than computation. In order to benefit from current and future trends in processor technology we must discover, understand, and exploit the available parallelism in machine learning. Taking advantage of a parallel execution of machine learning systems allow searching a larger space and reaching better solutions, and increasing the range of applications where it can be used.
  • WEEK 1
    • Intro to Big Data Analytics
    • Reading
      • Mining of Massive Data Sets
      • Machile Learning for Hackers
      • Data Revolution
    • Explore healthcare datasets
  • WEEK 2
    • Intro to Big Data Analytics and Healthcare
    • Reading
      • Mining Clinical Data
      • Predicting Data Mining
    • Explore Software
  • WEEK 3
    • Explore software (cont.)
    • Reading
      • Scaling up Machine Learning
  • WEEK 4
    • Student Presentations
    • Assessment and Project definition
  • WEEK 5-8
    • Implementation
    • Assessment
    • paper submission
  • WEEK 9-12
    • Implementation
    • Assessment
    • paper submission
  • WEEK 13-15
    • Presentations
    • Future work