Google Neural Network Produces Psychedelic Imagery

A look at the implications of a promising discovery by researchers at Google.

Artificial neural networks are increasingly being used to enable technologies such as image recognition, handwriting recognition, and speech recognition. But what would happen if instead of training neural networks to recognize features in images, you flipped the process on its head and trained it to emphasize those features in other images? Google's researchers put that question to the test and discovered to their surprise that the neural networks were able to generate new dreamlike images, even just out of white noise. The decidedly psychedelic results range from beautiful, to nightmarish.


In the pictures below, the neural network was trained to enhance different types of features in random noise and then gradually tweaked toward the interpretation that the researchers were looking for:

The process isn't perfect; for example when asked to classify a dumbbell it provided pictures of a dumbbell attached to a disembodied human arm:

The fact that the sample images used in the experiment contained a high proportion of images of animals explains the bizarre results below (we can only imagine what might have happened if Google safe search wasn't switched on).

"This network was trained mostly on images of animals, so naturally it tends to interpret shapes as animals. But because the data is stored at such a high abstraction, the results are an interesting remix of these learned features."

No one can deny the bizarre likeness between the images and reports of psychedelic hallucinations. We have long known that hallucinogenic drugs have a unique ability to make us see relationships that do not really exist, which is precisely what the neural networks were asked to look for in the images above. Perhaps this explains the images' psychedelic nature. 

"Even a relatively simple neural network can be used to over-interpret an image, just like as children we enjoyed watching clouds and interpreting the random shapes". 

But these neural networks aren't just useful for creating trippy wallpapers for your desktop; the technology also helps enable you to run an image search using nothing but an image. To read more about this project, check out Google's development blog. The project couldn't help but remind me of a fascinating project that successfully reconstructed video footage from human brain activity, which I blogged about a few years ago at Nature's Scitable blog.

If and when the technologies behind these two projects are merged, I'm sure we can expect even more exciting results.

Follow Neurobonkers on TwitterFacebookGoogle+RSS, or join the mailing list to get each week's post straight to your inbox. 

A still from the film "We Became Fragments" by Luisa Conlon , Lacy Roberts and Hanna Miller, part of the Global Oneness Project library.

Photo: Luisa Conlon , Lacy Roberts and Hanna Miller / Global Oneness Project
Sponsored by Charles Koch Foundation
  • Stories are at the heart of learning, writes Cleary Vaughan-Lee, Executive Director for the Global Oneness Project. They have always challenged us to think beyond ourselves, expanding our experience and revealing deep truths.
  • Vaughan-Lee explains 6 ways that storytelling can foster empathy and deliver powerful learning experiences.
  • Global Oneness Project is a free library of stories—containing short documentaries, photo essays, and essays—that each contain a companion lesson plan and learning activities for students so they can expand their experience of the world.
Keep reading Show less

Four philosophers who realized they were completely wrong about things

Philosophers like to present their works as if everything before it was wrong. Sometimes, they even say they have ended the need for more philosophy. So, what happens when somebody realizes they were mistaken?

Sartre and Wittgenstein realize they were mistaken. (Getty Images)
Culture & Religion

Sometimes philosophers are wrong and admitting that you could be wrong is a big part of being a real philosopher. While most philosophers make minor adjustments to their arguments to correct for mistakes, others make large shifts in their thinking. Here, we have four philosophers who went back on what they said earlier in often radical ways. 

Keep reading Show less

The history of using the Insurrection Act against Americans

Numerous U.S. Presidents invoked the Insurrection Act to to quell race and labor riots.

The army during riots in Washington, DC, after the assassination of civil rights activist Martin Luther King Jr., April 1968.

Photo by Michael Ochs Archives/Getty Images
Politics & Current Affairs
  • U.S. Presidents have invoked the Insurrection Act on numerous occasions.
  • The controversial law gives the President some power to bring in troops to police the American people.
  • The Act has been used mainly to restore order following race and labor riots.
Keep reading Show less

Experts are already predicting an 'active' 2020 hurricane season

It looks like a busy hurricane season ahead. Probably.

Image source: Shashank Sahay/unsplash
Surprising Science
  • Before the hurricane season even started in 2020, Arthur and Bertha had already blown through, and Cristobal may be brewing right now.
  • Weather forecasters see signs of a rough season ahead, with just a couple of reasons why maybe not.
  • Where's an El Niño when you need one?

Welcome to Hurricane Season 2020. 2020, of course, scoffs at this calendric event much as it has everything else that's normal — meteorologists have already used up the year's A and B storm names before we even got here. And while early storms don't necessarily mean a bruising season ahead, forecasters expect an active season this year. Maybe storms will blow away the murder hornets and 13-year locusts we had planned.

NOAA expects a busy season

According to NOAA's Climate Prediction Center, an agency of the National Weather Service, there's a 60 percent chance that we're embarking upon a season with more storms than normal. There does, however, remain a 30 percent it'll be normal. Better than usual? Unlikely: Just a 10 percent chance.

Where a normal hurricane season has an average of 12 named storms, 6 of which become hurricanes and 3 of which are major hurricanes, the Climate Prediction Center reckons we're on track for 13 to 29 storms, 6 to 10 of which will become hurricanes, and 3 to 6 of these will be category 3, 4, or 5, packing winds of 111 mph or higher.

What has forecasters concerned are two factors in particular.

This year's El Niño ("Little Boy") looks to be more of a La Niña ("Little Girl"). The two conditions are part of what's called the El Niño-Southern Oscillation (ENSO) cycle, which describes temperature fluctuations between the ocean and atmosphere in the east-central Equatorial Pacific. With an El Niño, waters in the Pacific are unusually warm, whereas a La Niña means unusually cool waters. NOAA says that an El Niño can suppress hurricane formation in the Atlantic, and this year that mitigating effect is unlikely to be present.

Second, current conditions in the Atlantic and Caribbean suggest a fertile hurricane environment:

  • The ocean there is warmer than usual.
  • There's reduced vertical wind shear.
  • Atlantic tropical trade winds are weak.
  • There have been strong West African monsoons this year.

Here's NOAA's video laying out their forecast:

But wait.

ArsTechnica spoke to hurricane scientist Phil Klotzbach, who agrees generally with NOAA, saying, "All in all, signs are certainly pointing towards an active season." Still, he notes a couple of signals that contradict that worrying outlook.

First off, Klotzbach notes that the surest sign of a rough hurricane season is when its earliest storms form in the deep tropics south of 25°N and east of the Lesser Antilles. "When you get storm formations here prior to June 1, it's typically a harbinger of an extremely active season." Fortunately, this year's hurricanes Arthur and Bertha, as well as the maybe-imminent Cristobal, formed outside this region. So there's that.

Second, Klotzbach notes that the correlation between early storm activity and a season's number of storms and intensities, is actually slightly negative. So while statistical connections aren't strongly predictive, there's at least some reason to think these early storms may augur an easy season ahead.

Image source: NOAA

Batten down the hatches early

If 2020's taught us anything, it's how to juggle multiple crises at once, and layering an active hurricane season on top of SARS-CoV-2 — not to mention everything else — poses a special challenge. Warns Treasury Secretary Wilbur Ross, "As Americans focus their attention on a safe and healthy reopening of our country, it remains critically important that we also remember to make the necessary preparations for the upcoming hurricane season." If, as many medical experts expect, we're forced back into quarantine by additional coronavirus waves, the oceanic waves slamming against our shores will best be met by storm preparations put in place in a less last-minute fashion than usual.

Ross adds, "Just as in years past, NOAA experts will stay ahead of developing hurricanes and tropical storms and provide the forecasts and warnings we depend on to stay safe."

Let's hope this, at least, can be counted on in this crazy year.

Scroll down to load more…