Do androids dream of electric sheep? Actually, it's not far off.
Artificial neural networks have taken giant leaps in image classification. And yet experts actually know very little about how they work - or why they fail.
In order to visualize what's going on, three software engineers at Google decided to turn the DeepDream neural network on its head. Alexander Mordvintsev, Christopher Olah and Mike Tyka asked their artifical intelligence bot to enhance an image in such as way as to elicit a particular interpretation - say, a banana.
"Start with an image full of random noise," said the engineers, "then gradually tweak the image towards what the neural net considers a banana. By itself, that doesn’t work very well, but it does if we impose a prior constraint that the image should have similar statistics to natural images, such as neighboring pixels needing to be correlated."
Hey look! It generated a banana. At least, something that you or I can recognize as bananas.
Now here's the really wacky bit. Neural networks that were trained to discriminate between different kinds of images also develop the ability to generate images too.
As in, to think. To create. To "dream".
So how are these neural networks coming up with original images?
Like you or I, they need a source of inspiration. A memory. An idea.
"We just start with an existing image [of sky] and give it to our neural net. We ask the network: 'Whatever you see there, I want more of it!'"
This creates a feedback loop: if a cloud looks a little bit like a bird, the network will make it look more like a bird. This in turn will make the network recognize the bird even more strongly on the next pass and so forth, until a highly detailed bird appears, seemingly out of nowhere.
"The results are intriguing - 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."
"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."
"This technique gives us a qualitative sense of the level of abstraction that a particular layer has achieved in its understanding of images. We call this technique Inceptionism in reference to the neural net architecture used."
See the team's Inceptionism gallery for more pairs of images and their processed results.
The coolest thing about this process is that the deeper you go, the more creativity you find.
The engineers found that if they apply the algorithm, over and over, on the same image, as well as zoom in on the most complex or interesting parts as they go, an endless stream of impressions emerge.
Take a look at these neural network "dreams" generated purely from random noise.
What do you these of these robot "dreams"? Impressed? Inspired? Perplexed?
Visit Google's online Deep Dream Generator to upload your own images and have them interpreted.
Here's what happened when I ran some of my lucid dream digital paintings through it:
Tell us what you think of neural network creativity over in our forums.
A lot has happened in the last 5 months. But how did we go from business as usual to changing the face of the entire lucid dreaming supplements industry? It’s a story that I think will interest you – and you might even learn a thing or two in the process. When I was first taken on-board as Chief Lucidity Officer in 2016, one of the first things I was tasked with was taking a good look at our operations and giving things a bit of an overhaul.
What is reality? How can we define it - fit it into a box - so that whatever experiments we throw at it, our definition always holds true? I consciously observe the lucid dream world. It is real to me because the firing of neurons in my brain stem are interpreted as real sensory data by my brain. I could argue that lucid dreams constitute part of my reality.
To lucid dream, I recommend being able to remember at least one vivid dream per night. That will boost your self awareness in dreams (making lucidity more likely) and also means you can actually remember your lucid dreams. Which is nice. Here are four detailed tips on how to remember your dreams more frequently. And if you don't think you dream at all - trust me, you almost certainly do. It takes an extraordinarily rare sleep disorder to deprive someone of dream sleep.
Years ago, before I had my first lucid dream, I had a very specific idea about what a lucid dream would feel like. I thought it would be intense and magical and a little bit spooky. This turned out to be a pretty accurate representation. Becoming aware in the dreamstate is like entering another world. One where physical laws can be manipulated (there is no spoon, Neo) and your fantasies can come true in an instant. There's definitely something magical about that - and it's as if the lucid dream world is a living, breathing organism that can react to your very thoughts.
It is estimated that these wise and wily Indians have been using mugwort in their healing and ritual practices for 13,000 years, where it is known as the ‘dream sage’. They use the herb to promote good dreams, which they consider an essential aspect of normal human functioning! But that’s not all...
Experts agree that everyone is capable of having lucid dreams. Dreaming itself is a normal function of the mind. We all dream every night, even if we don't remember. And we all achieve conscious awareness while awake every single day. So what does it mean to combine these states? Why, the amazing ability to have conscious - or lucid - dreams. Sounds simple, doesn't it? So why do I keep hearing from people who say they can't achieve their first lucid dream?