Evolutionary Algorithms for Feature Selection

Feature selection is a very important technique in machine learning.We need to be able to solve it to produce models. Feature Selection requires heuristic processes to find an optimal machine learning subset. In the previous post we discussed the brute force algorithm as well as forward selection and backward elimination which were both not a great fit. What other options are there? We can use one of the most common optimization algorithms for multi-modal fitness landscapes: evolutionary algorithms. Evolutionary algorithm is a generic optimization technique mimicking the ideas of natural evolution.