'Machine Learning for Art', a collection of tools and educational resources which apply techniques from machine learning to arts and creativity, was utilized to output dreamy images from the paintings, and DeepDream, an experiment that visualizes the patterns learned by a neural networ     Similar to when a child watches clouds and tries to interpret random shapes, DeepDream overinterprets and enhances the patterns it sees in an image. 

Neural Style Transfer is a computer vision technique that allows us to recompose the content of an image in the style of another. It takes two images - a content image and a style reference image - and blends them together so that the resulting output image retains the core elements of the content image, but appears to be "painted" in the style of the reference image.

For the detailed original source code and reference, please check out the About section.