A comparison of linear genetic programming and neural networks in medical data mining

TLDR

Acceleration of runtime is especially important when operating with complex data sets in real‑world applications. The study introduces a new form of linear genetic programming. The authors accelerate linear GP by eliminating intron code and using a demetic parallelization scheme, then evaluate its performance on medical classification benchmarks against neural networks. The results indicate that GP performs comparably to neural networks in classification accuracy and generalization.

Abstract

We introduce a new form of linear genetic programming (GP). Two methods of acceleration of our GP approach are discussed: 1) an efficient algorithm that eliminates intron code and 2) a demetic approach to virtually parallelize the system on a single processor. Acceleration of runtime is especially important when operating with complex data sets, because they are occurring in real-world applications. We compare GP performance on medical classification problems from a benchmark database with results obtained by neural networks. Our results show that GP performs comparably in classification and generalization.