Machine learning & AI
North Carolina State University researchers have developed a technique that reduces training time for deep learning networks by more than 60 percent without sacrificing accuracy, accelerating the development of new artificial ...
Apr 8, 2019
0
384
Machine learning & AI
Choosing an internship placement is a key step for many students, as an internship can have a substantial impact on their professional development. Researchers at Universitas Pendidikan Ganesha, in Indonesia, have recently ...
Computer Sciences
As artificial intelligence systems learn to better recognize and classify images, they are becoming highly-reliable at diagnosing diseases, such as skin cancer, from medical images. But as good as they are at detecting patterns, ...
Feb 25, 2019
0
26
Other
A team of researchers affiliated with several institutions in the U.K. has found that cascade effects are more to blame for poor performance by London's commuter train system than are mechanical failures. In their paper published ...
Energy & Green Tech
When the UK government cancelled its plans to electrify train lines across Wales, the Midlands and the north of England, and cut back on the Great Western rail network electrification, it brought a premature end to a rail ...
Jan 30, 2019
0
1
Automotive
A novel model developed by MIT and Microsoft researchers identifies instances in which autonomous systems have "learned" from training examples that don't match what's actually happening in the real world. Engineers could ...
Jan 25, 2019
1
102
Computer Sciences
Researchers at the University of Wisconsin-Madison and Amherst College have recently introduced a new form of steganography in the domain of machine learning called "training set camouflage." Their framework, outlined in ...
Computer Sciences
A team led by the University of California San Diego has developed a neuroinspired hardware-software co-design approach that could make neural network training more energy-efficient and faster. Their work could one day make ...
Dec 19, 2018
0
88
Computer Sciences
Researchers at Google have recently developed a new technique for synthesizing a motion blurred image, using a pair of un-blurred images captured in succession. In their paper, pre-published on arXiv, the researchers outlined ...
Machine learning & AI
Small imperfections in a wine glass or tiny creases in a contact lens can be tricky to make out, even in good light. In almost total darkness, images of such transparent features or objects are nearly impossible to decipher. ...
Dec 12, 2018
0
45
