Microsoft’s deep learning system is far better than humans and Google
Microsoft Research has again come up with the newest type of artificial intelligence called deep learning.
The new academic paper, employees in the Asian office of the tech giant’s research arm say their latest deep learning system can outperform humans by one metric.
According to the paper –“The Microsoft creation got a 4.94 percent error rate for the correct classification of images in the 2012 version of the widely recognized ImageNet data set, compared with a 5.1 percent error rate among humans.” The challenge involved identifying objects in the images and then correctly selecting the most accurate categories for the images, out of 1,000 options. Categories included “hatchet,” “geyser,” and “microwave.”
Deep learning is a process of training artificial neural networks on lots of information derived from images, audio, and other inputs, and then presenting the systems with new information and receiving inferences about it in response.
Few Microsoft researchers Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun collectively wrote in a paper that “To the best of our knowledge, our result surpasses for the first time the reported human-level performance on this visual recognition challenge.”
The researchers wrote that “The Artificial Intelligence watchers should have that type of paying attention and Microsoft should also be given more credibility when it comes to deep learning, where web companies like Google and Facebook compete for talent.
They further wrote that “While our algorithm produces a superior result on this particular dataset, this does not indicate that machine vision outperforms human vision on object recognition in general.” “On recognizing elementary object such as the Pascal VOC task, machines still have obvious errors in cases that are trivial for humans. Nevertheless, we believe that our results show the tremendous potential of machine algorithms to match human-level performance on visual recognition.”
The new technology has thus improved the Google’s award-winning GoogLeNet system by 26 percent, as it performed with 6.66 percent error, the Microsoft researchers claim.
This success is achieved from the program of Microsoft’s Project Adam work, which was completed last year.
The further detail about the new system is enclosed in the the paper (PDF).
Where is the off of the paper?