GSGP-CUDA — A CUDA framework for Geometric Semantic Genetic Programming

Geometric Semantic Genetic Programming (GSGP) is a state-of-the-art machine learning method based on evolutionary computation. GSGP performs search operations directly at the level of program semantics, which can be done more efficiently than operating syntax like most GP systems. Efficient implementations in C++ exploit this fact, but not to its full potential. This paper presents GSGP-CUDA, first CUDA implementation and efficient, exploits intrinsic parallelism using GPUs. Results show speedups greater 1,000× relative sequential implementation, during model training process. Additionally, our allows user seamlessly make inferences over new data through best evolved model, opening possibility Big Data problems.