Thanks to the use of GPUs, Microsoft researchers achieved record results on ImageNet, a prestigious image-recognition benchmark.
Compared to last year, Microsoft’s system cut the top-5 error rate by half, correctly classifying images within 1,000 pre-defined categories more than 96 percent of the time. Their system uses a 152-layer neural network, which is nearly five times deeper than the state of the art.
The researchers published a paper that provides more information on the deep learning framework used to win the ImageNet benchmark.
Read more on the NVIDIA blog >>