Microsoft Says AI-Powered Windows Updates Have Reduced Crashes

Microsoft has invested heavily in AI and machine learning, but you wouldn’t know it from how little attention it gets compared with Google. Microsoft is using its machine learning technology to address something all long-term Windows users have experienced: faulty updates. Microsoft says that AI can help identify systems that will play nicely with updates, allowing the company to roll new versions out more quickly with fewer crashes

It seems like we can’t get a single Windows update without hearing some stories of how it completely broke one type of system or another. You have to feel for Microsoft a little — the Windows ecosystem is maddeningly complex with uncountable hardware variants. Microsoft started using AI to evaluate computers with Windows 10, version 1803 (the April 2018 Update). It measured six PC health stats, assessed update outcomes, and loaded all the data into a machine learning algorithm. This tells Microsoft which computers are least likely to encounter problems with future updates. 

By starting with the computers with the “best” update compatibility, Microsoft can push new features to most users in short order. With most OS rollouts, things move very slowly at first while companies remain vigilant for issues. PCs determined to have likely issues by the AI will get pushed down the update queue while Microsoft zeros in on the problems. 

The ML models seem effective, even if Microsoft didn’t bother to label the Y-axis.

The first AI-powered employment was a success, with adoption rates higher than all previous Windows 10 updates. Microsoft expanded its original six PC metrics to a whopping 35 as of the Windows 1903 rollout (May 2019). The company claims this makes update targeting even more accurate. This does not guarantee perfect updates, though. Microsoft’s blog post glosses over 1809 update from late 2018. That rollout used AI technology, but you might recall the widespread file deletion bug that caused Microsoft to pause the release. AI might help determine compatibility, but it can’t account for unknown bugs like that. 

Still, Microsoft is happy with the results from its machine learning deployments. According to the new blog post, systems chosen for updates by the algorithm have fewer than half as many system uninstalls, half as many kernel-mode crashes, and one-fifth as many post-update driver conflicts. Hopefully, you can look forward to fewer Windows update issues going forward, and you’ll have AI to thank.

Now read:

from ExtremeTechExtremeTech

from Blogger

Tottenham v Bayern Munich: Jan Vertonghen ‘important part of project’, says Pochettino

Tottenham manager Mauricio Pochettino says defender Jan Vertonghen is “an important part of my project” as they prepare to face Bayern Munich.

from BBC News – London

from Blogger

NASA’s TESS Satellite Spots Star Being Ripped Apart by Black Hole

NASA’s Transiting Exoplanet Survey Satellite (TESS) is orbiting the Earth to search for alien worlds, but it spotted something much different recently. NASA says TESS observed a rare phenomenon known as a “tidal disruption event.” As TESS watched from a safe distance, a star spiraled toward a black hole before being torn to shreds.

TESS is a followup to the dearly departed Kepler Space Telescope. Whereas Kepler focused on small parts of the sky out to great distances, TESS aims to search for exoplanets across the entire sky out to a distance of about 300 light years. It uses the same transit method as Kepler for spotting exoplanets: when a planet passes in front of its host star, there’s a small dip in brightness. TESS watches for changes in brightness, and that’s how it spotted the tidal disruption event. 

The data from TESS shows a distant object getting brighter over the course of several days in January 2019. A tidal disruption event like this occurs when a star passes too close to a black hole. It becomes trapped in the black hole’s gravity and spirals in toward the event horizon. In the process, the extreme gravity breaks the star apart into an elongated stream of gas. Some of the matter escapes into space, but most of it forms an accretion disk around the black hole and is eventually consumed. 

TESS saw the first hint of the event now known as ASASSN-19bt on January 21st, 2019. It took place about 375 million light years away in a galaxy called 2MASX J07001137-6602251. The black hole is believed to be 6 million times as massive as the sun. Luckily, the break-up of the star was quite bright, and it happened in the satellite’s continuous viewing zone above the south pole. 

TESS only transmits data to Earth every two weeks, and it needs to be processed at NASA’s Ames Research Center before anyone can evaluate it. So, no one knew TESS had seen ASASSN-19bt until March. The All-Sky Automated Survey for Supernovae (ASAS-SN) is a network of robotic telescopes designed to detect events like ASASSN-19bt. However, ASAS-SN didn’t see the event until a week after TESS. Astronomers were able to gather data from ASASSN-19bt with the ASAS-SN array as usual before they knew anything about TESS’s observation. 

Having the data from TESS allows scientists to track how ASASSN-19bt behaved when it was still too dim for other instruments to see. The smooth increase in brightness detected by TESS also confirms this was a tidal disruption event and not another high-energy outbursts like a supernova. The TESS observational campaign is still ongoing, so there’s still time to spot some more tidal disruption events. We’re hoping for exoplanets, too.

Now read:

from ExtremeTechExtremeTech

from Blogger