Parallel exhaustive search vs. evolutionary computation in a large real world network search space

This work examines a novel method that provides a parallel search of a very large network space consisting of fisheries management data. The parallel search solution is capable of determining global maxima of the search space using exhaustive search, compared to local optima located by machine learning solutions such as evolutionary computation. The actual solutions from the best machine learning technique, called Probabilistic Adaptive Mapping Developmental Genetic Algorithm, are compared by a fisheries expert to the global maxima solutions returned by parallel search. The time required for parallel search, for both CPU and GPU-based solutions, are compared to those required for machine learning solutions. The GPU parallel computing solution was found to have a speedup of 12x over a multi-threaded CPU solution. An expert found that overall the machine learning solutions produced more interesting results by locating local optima than global optima determined by parallel processing.