Interestingly, the new machine chose to focus on cats. Dean says,"We never told it during the training 'this is a cat'. It basically invented the concept of a cat".
In a published report, the team states, "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. We also find that the same network is sensitive to other high-level concepts such as cat faces and human bodies. Starting with these learned features, we trained our network to obtain 15.8 percent accuracy in recognising 20,000 object categories from ImageNet, a leap of 70 percent relative improvement over the previous state-of-the-art".
0 comments:
Post a Comment