Skip to main content

Home/ Digit_al Society/ Group items tagged save

Rss Feed Group items tagged

dr tech

Wikipedia is facing an existential crisis. Can gen Z save it? | Stephen Harrison | The ... - 0 views

  •  
    "The world's most important knowledge platform needs young editors to rescue it from chatbots - and its own tired practices"
dr tech

UK startup uses AI to discover new rare earth-free magnet for EVs - 0 views

  •  
    "A UK-based startup has used an AI algorithm to identify a previously unknown kind of rare-earth free magnet, in a potential breakthrough for how we discover and create new materials. Materials Nexus, headquartered in London, used its machine learning algorithm to identify and analyse over 100 million combinations of materials that could produce a viable rare-earth free magnet."
dr tech

Mapping the landscape of histomorphological cancer phenotypes using self-supervised lea... - 1 views

  •  
    "Cancer diagnosis and management depend upon the extraction of complex information from microscopy images by pathologists, which requires time-consuming expert interpretation prone to human bias. Supervised deep learning approaches have proven powerful, but are inherently limited by the cost and quality of annotations used for training. Therefore, we present Histomorphological Phenotype Learning, a self-supervised methodology requiring no labels and operating via the automatic discovery of discriminatory features in image tiles. Tiles are grouped into morphologically similar clusters which constitute an atlas of histomorphological phenotypes (HP-Atlas), revealing trajectories from benign to malignant tissue via inflammatory and reactive phenotypes. These clusters have distinct features which can be identified using orthogonal methods, linking histologic, molecular and clinical phenotypes. Applied to lung cancer, we show that they align closely with patient survival, with histopathologically recognised tumor types and growth patterns, and with transcriptomic measures of immunophenotype. These properties are maintained in a multi-cancer study."
dr tech

As the Trump administration purges web pages, this group is rushing to save them : NPR - 0 views

  •  
    "While the Trump administration's scrubbing of federal web pages presents a notable example of the severed links issue, it's long been an epidemic. A Pew Research Center study published last year found that roughly 38% of web pages on the internet that existed in 2013 were no longer accessible as of 2023. According to a Harvard Law Review study published in 2014, about half of all links cited in U.S. Supreme Court opinions no longer led to the original source material. Kahle, who early on recognized the ephemeral nature of the web, said the rapid deterioration of the living web is a serious threat to historical preservation. "We're building our culture on shifting sands," he said."
« First ‹ Previous 61 - 64 of 64
Showing 20 items per page