Project Title  Parallel Implementation of Bayesian Network Structure Learning Algorithms 
Summary  The undergraduate intern will work with a mentor and a PH.D. student in order to optimize Bayesian Network structure learning algorithms for processing via CUDA. The student will then utilize those algorithms using the Blue Waters multiGPU system. 
Job Description  The goal of the undergraduate internship will be modifying existing Bayesian network learning algorithms for use within a parallel environment. Construction and scoring of Bayesian networks is NPcomplete, but heuristic algorithms have been developed to reduce the search space. The K2, Markov Chain Monte Carlo (MCMC), and Bayesian Network Power Constructor (BNPC) learning algorithms will be studied by the intern and then implemented using CUDA. We will then use these algorithms in conjunction with large genomic data sets to infer interactions among genes and groups of genes using Blue Waters supercomputing resources. The intern will document all steps involved with the optimization and utilization of these algorithms and will be encouraged to publish their findings. 
Conditions/Qualifications  Undergraduate students at the University of Akron; Must have a good understanding of programming concepts; Previous experience with C/C++ or Java programming 
Start Date  06/08/2015 
End Date  05/31/2016 
Location  Computer Science Department, The University of Akron, Akron Ohio USA 
Interns  Joe Haddad
