Computer Sciences

SPFCNN-Miner: A new classifier to tackle class-unbalanced data

Researchers at Chongqing University in China have recently developed a cost-sensitive meta-learning classifier that can be used when the training data available is high-dimensional or limited. Their classifier, called SPFCNN-Miner, ...

Machine learning & AI

Smarter training of neural networks

These days, nearly all the artificial intelligence-based products in our lives rely on "deep neural networks" that automatically learn to process labeled data.

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 ...

Machine learning & AI

An AI-based recommendation system for internship placements

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

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

WaveGlow: A flow-based generative network to synthesize speech

A team of researchers at NVIDIA has recently developed WaveGlow, a flow-based network that can generate high-quality speech from melspectrograms, which are acoustic time-frequency representations of sound. Their method, outlined ...

Computer Sciences

Supercomputing speeds up deep learning training

A team of researchers from the University of California, Berkeley, the University of California, Davis and the Texas Advanced Computing Center (TACC) published the results of an effort to harness the power of supercomputers ...

page 1 from 2