Machine Learning & AI

New technique cuts AI training time by more than 60 percent

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 ...

Computer Sciences

Teaching machines to reason about what they see

A child who has never seen a pink elephant can still describe one—unlike a computer. "The computer learns from data," says Jiajun Wu, a Ph.D. student at MIT. "The ability to generalize and recognize something you've never ...

Machine Learning & AI

Clarifying how artificial intelligence systems make choices

Artificial intelligence (AI) and machine learning architectures such as deep learning have become integral parts of our daily lives—they enable digital speech assistants or translation services, improve medical diagnostics ...

Computer Sciences

A new approach for low-resource machine transliteration using RNNs

A team of researchers at Universite du Quebec a Montreal and Vietnam National University Ho Chi Minh (VNU-HCM) have recently developed an approach for machine transliteration based on recurrent neural networks (RNNs). Transliteration ...

Computer Sciences

A new technique for synthesizing motion-blurred images

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 ...

Computer Sciences

A new approximate computing approach using CNNs

Researchers at Fukuoka University, in Japan, have recently proposed a design methodology for configurable approximate arithmetic circuits. As part of their study, published on ResearchGate, they applied their method to a ...

Computer Sciences

ColorUNet: A new deep CNN classification approach to colorization

A team of researchers at Stanford University has recently developed a CNN classification method to colorize grayscale images. The tool they devised, called ColorUNet, draws inspiration from U-Net, a fully convolutional network ...

page 2 from 9