Newscycle Solutions, a supplier of real-time content for
financial industries, corporate intelligence and the news media, has gotten a
patent for a new technique in unsupervised learning, the company says. The
technology uses methods in the NewsEdge software for clustering like content.
“The
challenge of unsupervised learning is this: take a huge sample of individuals
(or individual things, like news articles), and group like-with-like,” said
Lawrence C. Rafsky, chief artificial intelligence/machine learning scientist at
Acquire Media, a Newscycle company. Rafsky created the technique in
collaboration with Jonathan A. Marshall.
Rafsky said
that there are numerous other techniques for unsupervised learning, but the
Newscycle-patented solution is unique in that it runs in real time and gets an
exact answer to the underlying combinatorial minimization problem. “It’s
super-fast and we get the exact answer, whereas other techniques just arrive at
an approximation,” he said.
Newscycle’s
NewsEdge content-as-a-service solution uses the algorithm to group more than
750,000 news articles a day into buckets of single-themed news events,
continuously throughout the day, in real time. However, its creators note that
it could have applications in other industries as well.
U.S. Patent
#10,216,829 was issued Feb 26, 2019.
No comments:
Post a Comment
For now, we're opening this blog to Anonymous comments. This will continue as long as civility rules. Disagree as you may, just keep it clean and stay on topic. No profanity, and no name calling. We reserve the right to moderate such comments, though the person who made it may come back and reword their message in a more civil way.