AI | Boomers Daily

Hear the latest science news, with Benjamin Thompson and Shamini Bundell. This week, a computer beats the best human players in StarCraft II, and a huge study of insects and other arthropods.

In this episode:

00:51 Learning to play

By studying and experimenting, an AI has reached Grandmaster level at the video game Starcraft II. Research Article: Vinyals et al.; News Article: Google AI beats experienced human players at real-time strategy game StarCraft II

10:08 Research Highlights

A record-breaking lightning bolt, and identifying our grey matter’s favourite tunes. Research Highlight: Here come the lightning ‘megaflashes’; Research Highlight: Why some songs delight the human brain

12:24 Arthropods in decline

Researchers have surveyed how land-use change has affected arthropod diversity. Research article: Seibold et al.

18:30 News Chat

Young Canadians file a lawsuit against their government, an Alzheimer’s drug gets a second chance, and South Korean efforts to curb a viral epidemic in pigs.

From a Health IT Analytics online release:

The prototype revealed that using artificial intelligence and machine learning to examine certain combinations of vital signs and other biomarkers could strongly predict the likelihood of infection up to 48 hours in advance of clinical suspicion, including observable symptoms.

Royal Philips, in collaboration with the Defense Threat Reduction Agency (DTRA) and Defense Innovation Unit (DIU) of the US Department of Defense (DoD), are building a machine learning algorithm that will be able to detect an infection before a patient shows signs or symptoms.

The partnering organizations recently announced results from an 18-month project, called Rapid Analysis of Threat Exposure (RATE), the first large-scale exploration of pre-symptomatic infection in humans. The project aims to develop an early warning system that accelerates diagnosis and treatment of infection, containing the spread of communicable disease.