Google continue their innovation with a new researches aimed detect a cat on a picture, the project was tested to 10 million randomly selected YouTube video thumbnails over the course of three days, thanks to the artificial brain used consisting of up to an whooping 16,000 processor cores with a result 81.7 percent accuracy for human face detection as Google's Jeff Dean report.
Using a "deep learning algorithm" technique
Picking up on the most commonly occurring images featured on YouTube, the system achieved 81.7 percent accuracy in detecting human faces, 76.7 percent accuracy when identifying human body parts and 74.8 percent accuracy when identifying cats.
“Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containing a face or not,” the team says in its paper, Building high-level features using large scale unsupervised learning, which it will present at the International Conference on Machine Learning in Edinburgh, 26 June-1 July.
“The network is sensitive to high-level concepts such as cat faces and human bodies. Starting with these learned features, we trained it to obtain 15.8 percent accuracy in recognizing 20,000 object categories, a leap of 70 percent relative improvement over the previous state-of-the-art [networks].”
If you like this article, please share it on facebook, tweet it and +1 it to spread it :) !