# Perceptron learning for non-linearly separable data

It is well known that perceptron learning will never converge for non-linearly separable data. This means that you cannot fit a hyperplane in any dimensions that would separate the two classes. Is it possible to do basis transformation to learn more complex decision boundaries for the apparently non-linearly separable data using perceptron classifier?

• By basis transformation, do you mean transforming your features, e.g. $(x,y)$ to $(x,y,x^2,y^2)$? – gunes Apr 3 '19 at 9:28
• Yes. Can I use this transformation and make the data linearly separable in some higher dimension and then apply perceptron? – bandit_king28 Apr 3 '19 at 9:30