Slashdot Mirror
Research Highlights How AI Sees and How It Knows What It's Looking At
anguyen8 writes Deep neural networks (DNNs) trained with Deep Learning have recently produced mind-blowing results in a variety of pattern-recognition tasks, most notably speech recognition, language translation, and recognizing objects in images, where they now perform at near-human levels. But do they see the same way we do? Nope. Researchers recently found that it is easy to produce images that are completely unrecognizable to humans, but that DNNs classify with near-certainty as everyday objects. For example, DNNs look at TV static and declare with 99.99% confidence it is a school bus. An evolutionary algorithm produced the synthetic images by generating pictures and selecting for those that a DNN believed to be an object (i.e. "survival of the school-bus-iest"). The resulting computer-generated images look like modern, abstract art. The pictures also help reveal what DNNs learn to care about when recognizing objects (e.g. a school bus is alternating yellow and black lines, but does not need to have a windshield or wheels), shedding light into the inner workings of these DNN black boxes.
Reminds me of the reverse OCR tumblr. It generates patterns of squiggles a human could never read but the OCR recognizes as a word.
http://reverseocr.tumblr.com/
Everytime I see this topic appear on Slashdot (Last time) I think:
You're putting a neural network (NN) through a classification process where it is fed this image as a "fixed input", where the input's constituent elements are constant, and you ask it to classify correctly the same way as a human would. The problem with this comparison is the human eye does not see a "constant" input stream; the eye captures a stream of images, each slightly skewed as your head moves and the images changes slightly. Based on this stream of slightly different images, the human identifies an object.
However, in this research, time and again a "team" shows a "fault" in a NN by taking a single, nonvarying image input to a NN and calling it a "deep flaw in the image processing network", and I just get a feeling that they're doing it wrong.
To your topic though: You better hope your car is not just taking one single still image and performing actions based on that. You better hope your car is taking a stream of images and making decisions, which would be a completely different class of problem than this.
There's also a tremendous gap between what we consider complex and what we consider simple. For example, the brain is complex. However, individual elements of our brains are incredibly simple. Basic chemical reactions. Neurons firing or not. It's the sheer number of simultaneous simple pieces working together that makes it complex.
Lots of simple AI algorithms all working together make the complexity. This isn't climbing a tree. It's one person poking at chemicals until they get high-energy combustible fuels, and another playing with paper to make paper airplanes better, and a third refining ceramics and metals to make them lighter and stronger and to handle different characteristics, and then they all get put together and you have a person on the moon.
The illusion is that you think we need to make a leap to get from here to there. There's never a leap. It's lots of small simple steps that get you there.
~Anguirel (lit. Living Star-Iron)
QA: The art of telling someone that their baby is ugly without getting punched.