Darwin, Lamarck, or Baldwin: Applying Evolutionary Algorithms to Machine Learning Techniques

Evolutionary Algorithms (EAs), inspired by biological mechanisms observed in nature, such as selection and genetic changes, have much potential to find the best solution for a given optimisation problem. Contrary to Darwin, and according to Lamarck and Baldwin, organisms in natural systems learn to adapt over their lifetime and allow to adjust over generations. Whereas earlier research was rather reserved, more recent research underpinned by the work of Lamarck and Baldwin, finds that these theories have much potential, particularly in upcoming fields such as epigenetics. In this paper, we report on some experiments with different evolutionary algorithms with the purpose to improve the accuracy of data mining methods. We explore whether and to what extent an optimisation goal can be reached through a calculation of certain parameters or attribute weightings by use of such evolutionary strategies. We provide a look at different EAs inspired by the theories of Darwin, Lamarck, and Baldwin, as well as the problem solving methods of certain species. In this paper we demonstrate that the modification of well-established machine learning techniques can be achieved in order to include methods from genetic algorithm theory without extensive programming effort. Our results pave the way for much further research at the cross section of machine learning optimisation techniques and evolutionary algorithm research.