Baidu has an image recognition system, Deep Image, developed using deep learning. The key components are a custom-built supercomputer dedicated to deep learning, new algorithms and large neural networks.
On one of the most challenging computer vision benchmarks, the ImageNet classification challenge, the system has achieved the best result to date, with a top – 5 error rate of 5.98% -a relative 10.2% improvement over the previous best result.
Chinese search engine company Baidu says it has built the world’s most-accurate computer vision system, dubbed Deep Image, which runs on a supercomputer optimized for deep learning algorithms. Baidu’s 5.98 percent error rate on the ImageNet object classification benchmark is better than Google’s 2014 ImageNet competition winning 6.66 percent error rate.