Sunday, July 05, 2015

the conscious mind and the photon interaction...,

guardian |  What do machines dream of? New images released by Google give us one potential answer: hypnotic landscapes of buildings, fountains and bridges merging into one.

The pictures, which veer from beautiful to terrifying, were created by the company’s image recognition neural network, which has been “taught” to identify features such as buildings, animals and objects in photographs.

They were created by feeding a picture into the network, asking it to recognise a feature of it, and modify the picture to emphasise the feature it recognises. That modified picture is then fed back into the network, which is again tasked to recognise features and emphasise them, and so on. Eventually, the feedback loop modifies the picture beyond all recognition.

At a low level, the neural network might be tasked merely to detect the edges on an image. In that case, the picture becomes painterly, an effect that will be instantly familiar to anyone who has experience playing about with photoshop filters:

 The pictures are stunning, but they’re more than just for show. Neural networks are a common feature of machine learning: rather than explicitly programme a computer so that it knows how to recognise an image, the company feeds it images and lets it piece together the key features itself.

But that can result in software that is rather opaque. It’s difficult to know what features the software is examining, and which it has overlooked. Fist tap John Kurman.


CNu said...

So my son is looking at this neural-network edge-detection imagery, and asks the oddest kwestin - "are mappers sure there's not a temporal aspect to these patterns?" i.e., are these only resolving edges as the program's designers/authors intend, but is this also part of what it's like to unconsciously queue and resolve multiple paths in spacetime?

Dale Asberry said...

Speaking of alkahest and the google algorithm...

John Kurman said...

Recursion is fun, isn't it? Notice, though the emptiness. Sure, you got infinite complex turtles all the way down, but missing those nonlocal entanglements. Sum over histories.

Ed Dunn said...

I found this one pretty interesting