[NSFW] The strange pictures thread

[justabubba]

not so much strange as majestic, the woolyback overlook, blue ridge mountains:

 

[azgreg]

 

[azgreg]

Anybody mention global warming?

 

[azgreg]

 

[RAMOSS]

 

[Mr Person]

 

[justabubba]

 

[RAMOSS]

 

[Dittohead not!]

 

[justabubba]

nashville after the tornado

 

[LadyMoonlight]

 

[justabubba]

 

[justabubba]

1918 - 1919 era baseball attire

 

[justabubba]

check this out; how many do you recognize?

Western Saloon Painting by Tim Joyner

 

[Mr Person]

RE: "Deep learning" / image recognition.

Ingenious strategies have been used to try to capture and thus explain in more detail what’s happening in such systems. In 2015, researchers at Google modified a deep-learning-based image recognition algorithm so that instead of spotting objects in photos, it would generate or modify them. By effectively running the algorithm in reverse, they could discover the features the program uses to recognize, say, a bird or building. The resulting images, produced by a project known as Deep Dream, showed grotesque, alien-like animals emerging from clouds and plants, and hallucinatory pagodas blooming across forests and mountain ranges. The images proved that deep learning need not be entirely inscrutable; they revealed that the algorithms home in on familiar visual features like a bird’s beak or feathers. But the images also hinted at how different deep learning is from human perception, in that it might make something out of an artifact that we would know to ignore.

(Overall subject is the difficulty/impossibility of working out why a deep learning AI made a decision it did. These are the ones that effectively program themselves based on observing how humans go about doing a thing.)

The Dark Secret at the Heart of AI

So:

Was read as:

 

[Mr Person]

Others at:

Inceptionism: Going deeper into Neural Networks - Google Photos

As if you could give a computer a whopping great dose of digital acid...

 

[Mr Person]

 

[justabubba]

RE: "Deep learning" / image recognition.

Ingenious strategies have been used to try to capture and thus explain in more detail what’s happening in such systems. In 2015, researchers at Google modified a deep-learning-based image recognition algorithm so that instead of spotting objects in photos, it would generate or modify them. By effectively running the algorithm in reverse, they could discover the features the program uses to recognize, say, a bird or building. The resulting images, produced by a project known as Deep Dream, showed grotesque, alien-like animals emerging from clouds and plants, and hallucinatory pagodas blooming across forests and mountain ranges. The images proved that deep learning need not be entirely inscrutable; they revealed that the algorithms home in on familiar visual features like a bird’s beak or feathers. But the images also hinted at how different deep learning is from human perception, in that it might make something out of an artifact that we would know to ignore.

(Overall subject is the difficulty/impossibility of working out why a deep learning AI made a decision it did. These are the ones that effectively program themselves based on observing how humans go about doing a thing.)

The Dark Secret at the Heart of AI

So:

Was read as:

the bottom right generated AI 'photo' background could be a riff off of starry, starry night

 

[longview]

People should not do hallucinogenic drugs, and computer algorithms should not synthesize their effects!
Interesting pictures though!

 

[azgreg]

Recycled phone cords.

 

[justabubba]

 

[justabubba]

 

[justabubba]

 

[justabubba]

 

[justabubba]