Wednesday, 22 May 2019

New framework improves performance of deep neural networks

North Carolina State University researchers have developed a new framework for building deep neural networks via grammar-guided network generators. In experimental testing, the new networks—called AOGNets—have outperformed existing state-of-the-art frameworks, including the widely-used ResNet and DenseNet systems, in visual recognition tasks.

* This article was originally published here

Endangered bird returned to S. Korean wild 40 years after extinction

An endangered bird was reintroduced to the wild by South Korean authorities Wednesday, four decades after it went extinct on the peninsula.

* This article was originally published here

LG will smarten home appliances with eyes and ears

LG has made news headlines recently because now it has its own artificial intelligence chip. LG is out to impress with its own chip for smart home products—to make them even smarter.

* This article was originally published here

Expert consensus published on use of imaging to guide heart attack treatment

Imaging provides a more precise diagnosis of a heart attack that can be used to individualise treatment. That's the main message of an expert consensus paper published today in European Heart Journal, a journal of the European Society of Cardiology (ESC), and presented at EuroPCR in Paris, France.

* This article was originally published here

PAL: A wearable system for context-aware health and cognition support

Researchers at MIT Media Lab have developed a wearable platform that provides real-time, personalized, and context-aware health and cognition support. Their system, called personalized active learner (PAL), was presented in a paper pre-published on arXiv.

* This article was originally published here