Correlation and NN

Hi,

After doing and EDA … ¿it’s a good practice to get rid of the correlated features before feeding in a fully connected NN? … or ¿should I let the NN try to figure out the relationships between the features, being present those correlated? …

BTW, EDA stands for Exploratory Data Analisys

In a nutshel, It’s doing some descriptive analysis (histograms, correlations, plots, get quantiles)… so that you can get to know your data well …

I most ML models and courses, and EDA it’s recommended before applying a model. I wanted to know, if that runs also for NN in Deep Learning, specifically … getting rid of the correlated variables

Best regards