AI for Data Science: Artificial Intelligence Frameworks and Functionality for Deep Learning, Optimization, and Beyond by Zacharias Voulgaris PhD & Yunus Emrah Bulut

Author:Zacharias Voulgaris PhD & Yunus Emrah Bulut [Voulgaris, Zacharias PhD & Bulut, Yunus Emrah]
Language: eng
Format: epub, azw3, pdf
Tags: Computers, Intelligence (AI) & Semantics, Computer Simulation, Programming, Algorithms
ISBN: 9781634624114
Google: jj1vDwAAQBAJ
Publisher: Technics Publications
Published: 2018-10-01T12:28:08.145046+00:00

Clearly, the new features are going to be correlated to the original ones, which we can verify as follows:

cor(Z[:,1], Z[:,21])

However, we’ll need easy access to all correlations among the various features. As such, it makes sense to compute all these correlations beforehand and store them in a variable that all functions can easily access:

global CM = cor(Z);

for i = 1:40

CM[i,i] = 0.0

end

Note that we set the correlation of each variable with itself to 0, to avoid allowing that value to dominate all the others.

Now, it’s time to define the fitness function for this problem, which should look something like this:

function ff2(X::Array{Bool, 1})

N = length(X)

f = collect(1:N) .* X

f = f[f .> 0]

n = length(f)

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.