Most artificial intelligence it is still built on a human labor base. Look inside an artificial intelligence algorithm and you will find something built with data that has been cured and tagged by an army of human workers.
Now, Facebook has shown how some artificial intelligence algorithms can learn to do useful work with much less human help. The company built an algorithm that learned how to recognize objects in images with little help from tags.
Facebook’s algorithm, called Seer (for SElf-supERvised), fed on more than a billion images taken from Instagram and decided for itself what objects looked like. Images with mustaches, skins, and pointed ears, for example, were collected in a pile. The algorithm was then given a small number of tagged images, including some tagged “cats”. He was then able to recognize images as well as an algorithm trained using thousands of tagged examples of each object.
“The results are impressive,” says Olga Russakovsky, an assistant professor at Princeton University who specializes in AI and computer vision. “Getting self-controlled learning to work is very difficult, and advances in this space have important subsequent consequences for improving visual recognition.”
Russakovsky says it is noteworthy that Instagram images were not hand-picked to facilitate independent learning.
Facebook research is a benchmark for an AI approach known as “self-controlled learning,” says Facebook chief scientist Yann LeCun.
LeCun pioneered the machine learning approach known as deep learning which involves feeding data to large artificial neural networks. About a decade ago, deep learning emerged as a better way to program machines to do all sorts of useful things, such as image classification and speech recognition.
But LeCun says the conventional approach, which requires “training” an algorithm by feeding it lots of tagged data, just won’t scale. “I’ve been advocating this whole idea of self-controlled learning for a long time,” he says. “In the long run, progress in AI will come from programs that just watch videos all day and learn like a baby.”
LeCun says self-controlled learning could have many useful applications, for example, learning to read medical images without the need to label so many scans and x-rays. He says a similar approach is already being used to automatically generate hashtags for Instagram images. And he says Seer technology could be used on Facebook to match ads to posts or to help filter out unwanted content.
Facebook research is based on steady progress in modifying deep learning algorithms to make them more efficient and effective. Self-controlled learning has previously been used to translate text from one language to another, but has been more difficult to apply to images than to words. LeCun says the research team developed a new way for algorithms to learn to recognize images even when a part of the image has been modified.
Facebook will launch some of the technology behind Seer, but not the algorithm itself, as it has been formed with data from Instagram users.
Aude Oliva, who heads MIT’s computational perception and cognition lab, says the approach “will allow us to take on more ambitious visual recognition tasks.” But Oliva says the sheer size and complexity of artificial intelligence algorithms like Seer, which can have billions or trillions of connections or neural parameters, is much more than a conventional image recognition algorithm with comparable performance. , also pose problems. These algorithms require huge amounts of computing power, straining the available supply of chips.
Alexei Efros, a professor at UC Berkeley, says the Facebook diary is a good demonstration of an approach he believes will be important in advancing AI: that machines learn for themselves through the use of “large amounts of data ”. And, as with most current advances in AI, he says, it is based on a number of other advances that have emerged from the Facebook team itself and other academic and industry research groups.
Bigger cable stories