Neural networks have proven tremendously successful at tasks like identifying objects in images, but how they do so remains largely a mystery.
On Wednesday, Carter’s team released a paper that offers a peek inside, showing how a neural network builds and arranges visual concepts.
Olah’s team taught a neural network to recognize an array of objects with ImageNet, a massive database of images.
Neural networks are composed of layers of what researchers aptly call neurons, which fire in response to particular aspects of an image.
Researchers trying to understand how neural networks function have been fighting a losing battle, he points out, as networks grow more complex and rely on vaster sums of computing power.
As an illustration, Olah pulls up an ominous photo of a fin slicing through turgid waters: Does it belong to a gray whale or a great white shark? As a human inexperienced in angling, I wouldn’t hazard a guess, but a neural network that’s seen plenty of shark and whale fins shouldn’t have a problem.
Neural networks are generally excellent at classifying objects in static images, but slip-ups are common-say, in identifying humans of different races as gorillas and not humans.
This article was summarized automatically with AI / Article-Σ ™/ BuildR BOT™.