# Using a point as an input for a perceptron

Can a point be used as the input for a perceptron/neural net?

The relationship between the two numbers that make up a 2D point does not affect the output, but does this not matter when the satisfactory weights are found?

If I wanted to use a point $$(x,y)$$ as an input for my perceptron, would I simply have two input nodes, one for $$x$$ and one for $$y$$?

Yes, you can do that. Nothing prevents it. Yes, you'd have two inputs, one for $$x$$ and one for $$y$$. You might want to normalize those values so they are in the range $$[-1,1]$$ or $$[0,1]$$.