DeepDream

DeepDream is a computer vision program created by Google which uses a convolutional neural network to find and enhance patterns in images via algorithmic pareidolia, thus creating a dreamlike hallucinogenic appearance in the deliberately over-processed images.

Google's program popularized the term (deep) "dreaming" to refer to the generation of images that desired activations in a trained deep network, and the term now refers to a collection of related approaches.

See also

• Algorithmic art
• Computer vision
• Procedural textures
• Texture synthesis

External links

• DeepDream @ Wikipedia.org
• deepdream @ GitHub - "The repository contains IPython Notebook with sample code, complementing Google Research blog post about Neural Network art."
• Inceptionism: Going Deeper into Neural Networks - "We train an artificial neural network by showing it millions of training examples and gradually adjusting the network parameters until it gives the classifications we want."
• DeepDream - a code example for visualizing Neural Networks
• Running Google’s Deep Dream on Windows (with or without CUDA) – The Easy Way
• Create Your Own Artificial Fever Dreams with Google’s "DeepDream"
• Afrofuturist artist Wagner James Au creates gorgeous portraits with Deep Dreaming - comments:
  • It sure looks like they were generated with Neural Style Transfer, not Deep Dreams. If it were Deep Dreams, there’d been hundreds of mutant doggies, eyeballs, and gazebos everywhere (or just very typical curved lines).
  • I’ve been using Deep Dream Generator, which has three options including the mutant things.
  • I played around with “DEEPART”.
  • It looks like the Deep Dream Generator page is somewhat misleading in the names: the “Deep Style” is probably Gatys’ Gram-matrix based Neural Style Transfer, and the “Thin Style” looks like one of the feed-forward network style transformation methods. Neither of those are Deep Dream methods. The Gatys method (“Deep Style”, most likely) is this one: https://arxiv.org/abs/1508.06576 Something I wrote with more background on Neural Style Transfer: https://research.adobe.com/image-stylization-history-and-future-part-3/