If art is what makes us human, how come Google’s bots can do it too?
DeepDream is a computer vision program created by Google engineer Alexander Mordvintsev which uses a convolutional neural network to find and enhance patterns in images via algorithmic pareidolia, thus creating a dream-like hallucinogenic appearance in the deliberately over-processed images.
This new software provide artists an opportunity to be creative like never before. With this fresh approach to art, there are questions about who should get credit for the artwork. Should it be the artist, the computer software, or the software’s creator, and is the final product really art?
The software is designed to detect faces and other patterns in images, with the aim of automatically classifying images. However, once trained, the network can also be run in reverse, being asked to adjust the original image slightly so that a given output neuron (e.g. the one for faces or certain animals) yields a higher confidence score. This can be used for visualizations to understand the emergent structure of the neural network better, and is the basis for the DeepDream concept. However, after enough reiterations, even imagery initially devoid of the sought features will be adjusted enough that a form of pareidolia results, by which psychedelic and surreal images are generated algorithmically. The optimization resembles Backpropagation, however instead of adjusting the network weights, the weights are held fixed and the input is adjusted.
For example, an existing image can be altered so that it is “more cat-like”, and the resulting enhanced image can be again input to the procedure. This usage resembles the activity of looking for animals or other patterns in clouds.
Applying gradient descent independently to each pixel of the input produces images in which adjacent pixels have little relation and thus the image has too much high frequency information. The generated images can be greatly improved by including a prior or regularizer that prefers inputs that have natural image statistics (without a preference for any particular image), or are simply smooth. For example, used the total variation regularizer that prefers images that are piecewise constant. Various regularizers are discussed further in. An in-depth, visual exploration of feature visualization and regularization techniques was published more recently.
You can view some Deep Dream artworks at this gallery: