Microsoft Neural Net Shows Deep Learning Can Get Way Deeper
Originally shared by Ward Plunet
Microsoft Neural Net Shows Deep Learning Can Get Way Deeper
the latest ImageNet winner is pointing to what could be another step in the evolution of computer vision—and the wider field of artificial intelligence. Last month, a team of Microsoft researchers took the ImageNet crown using a new approach they call a deep residual network. The name doesn’t quite describe it. They’ve designed a neural net that’s significantly more complex than typical designs—one that spans 152 layers of mathematical operations, compared to the typical six or seven.
http://www.wired.com/2016/01/microsoft-neural-net-shows-deep-learning-can-get-way-deeper/
Microsoft Neural Net Shows Deep Learning Can Get Way Deeper
the latest ImageNet winner is pointing to what could be another step in the evolution of computer vision—and the wider field of artificial intelligence. Last month, a team of Microsoft researchers took the ImageNet crown using a new approach they call a deep residual network. The name doesn’t quite describe it. They’ve designed a neural net that’s significantly more complex than typical designs—one that spans 152 layers of mathematical operations, compared to the typical six or seven.
http://www.wired.com/2016/01/microsoft-neural-net-shows-deep-learning-can-get-way-deeper/
Comments
Post a Comment