Do Conv-nets Dream of Psychedelic Sheep?

From top to bottom: input image, conv2-3x3_reduce, inception_4c-1 1. Made using deepdreamgenerator and public domain image from Yellowstone National Park NPS. The modern successes of deep learning are in part due to the universal approximation theorem developed by George Cybenko, Kurt Hornik, and others. The theorem in essence states that a neural network with at least one hidden layer and a non-linear activation function can generally approximate arbitrary continuous functions. In the past decade, the re-purposing of powerful GPUs for training deep networks unleashed the potential of the universal approximation theorem, fueling many new areas of business and research. In a deep learning model, many hidden layers can be stacked one on top of another like a skyward-reaching Tower of Babel, and internal representations can come to represent complicated abstractions and feature hierarchies. These representations can be part of a model predicting anything from the seemingly inconsequential such as nonsensical astrophysics acronyms, streaming video preferences, and dating matches; to the potentially grave: credit risk ratings, medical diagnoses, and dating matches.