Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
494005 | Swarm and Evolutionary Computation | 2016 | 11 Pages |
This paper describes the performance of the Brain Project, a distributed software tool for the formal modeling of numerical data using a hybrid neural-genetic programming technique. One of the most interesting characteristics of the Brain Project is its distributed implementation. Unlike many other parallel and/or distributed solutions the only requirement of the Brain Project is that the collaborating personal computers must be 64-bit Linux machines connected to Internet via the transmission control protocol/internet protocol. The performance of the Brain Project is clearly enhanced with the very simple parallelization scheme illustrated in the paper. Although the Brain Project presents many innovative solutions for the genetic programming research, this paper focuses mainly on its behavior in the distributed environment.