WSJ [paywall] – “America’s oldest federal cultural institution is experimenting with neural networks to help users search through some of its millions of digitized documents. The Library of Congress expects that artificial intelligence can help people search through its troves of digital information to glean new insights about the U.S.’s history. To that end, America’s oldest federal cultural institution is experimenting with AI technologies that are commonly employed by Facebook Inc. and Alphabet Inc.’s Google. The library has chosen three computer science and digital humanities experts to investigate how branches of artificial intelligence such as neural networks and computer vision can help humans sift through some of its millions of digitized items. Their work will culminate early next year in new online search prototypes…”