Skip to content
0:00 / 0:00

#deepdream#neuralnetworks#generativeart

Journey on the Deep Dream

Roger Luedecke

767 subscribers • 1 video on Hallway

YouTube
  • Recommended by 1 person: 1 on Hacker News.
  • May be out of date. Uploaded 11 years ago, in an area where tools change fast.

Beginner. No background in the topic needed.

597K views11 years ago1 recommendation

AI and machine learningGraphics and audioNeural networks and deep learningCreative coding

How Google's Deep Dream visualization technique recursively processes random noise to reveal the features learned by different neural network layers.

" A journey through all the layers of an artificial neural network. This video is made using a visualization technique applied to a neural network trained to recognize a broad range of images. Each frame is recursively fed back to the network starting with a frame of random noise. Every 100 frames (4 seconds) the next layer is targeted until the lowest layer is reached. Based on the work by Google researchers Alexander Mordvintsev, Christopher Olah and Mike Tyka. See googleresearch.blogspot.it/2015/07/deepdream-code-example-for-visualizing.html for more information." ~Johan Nordberg, original video creator. Original video by Johan Nordberg here. vimeo.com/132700334 special thanks to Ektoplazm for inspiration Music: Journey on the Sunset by Sam'adhi on the Low Tide VA ektoplazm.com/free-music/low-tide

Why it's here

1 person recommends this

What people say. Recommended as an excellent visual example of Google's Deep Dream neural network visualization.

matt4077on Hacker News • Recommends

On “Feature Visualization: How neural nets build up their understanding of images”

have you seen "Deep Dream"? link to this video and link are excellent examples. I believe for anybody who has ever tried psychedelics seeing these was a watershed moment. It seems almost impossible that an algorithm could so faithfully reproduce the experience without somehow having recreated some fundamental structure of the human brain. That is compounded by the fact that this wasn't the result of actually trying to do so, but of an open-ended experiment of creating feedback loops in NN layers.

lelandbateyon Hacker News • Mentions

On “Image Synthesis from Yahoo's open_nsfw”

Indeed, and let's not forget the extended example of the video of random noise fed into Google's Deep Dream system: link to this video

rwinnon Hacker News • Mentions

On “Show HN: Spotter – Search for copies of videos on the internet”

Got the results now, posted one of my own videos I know has been reuploaded multiple times: 0 total copies were found with 0 total views Original: link Some known re-uploads: link link link to this video --- Great concept, would love if it actually worked.