Latest topics
» SCAMMER ALERT! - Judy aka Quartz Crystal the Source Player is PLAYING You for DONATIONS! - PLUS A CULT MEMBER CONVERSATION
AI trained on old scientific papers makes discoveries humans missed EmptyToday at 12:58 am by RamblerNash

» Dave Schmidt (Meta 1 Coin) - No Paperwork?
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 11:46 pm by PurpleSkyz

» California Approves $3.2 Billion Bond For High Speed Train To Nowhere
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 11:40 pm by PurpleSkyz

» November's Spectacular Full Moon Rising - Don't Miss The "Full Beaver Moon"
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 8:29 pm by PurpleSkyz

» Natural Health Under Attack
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 5:31 pm by PurpleSkyz

» Th!nk Colab Sunday November 10, 2019
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 4:48 pm by Consciousness Of Economic

» Paul Craig Roberts – ‘We Must Act Now to Save Julian Assange & the Rule of Law’
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 11:40 am by PurpleSkyz

» USB stick found with astonishing 1900s images of planets and UFOs in space
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 11:34 am by PurpleSkyz

» The Ocean Cleanup - RIVERS | INTERCEPTOR | Lost Teddy bear
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 11:28 am by PurpleSkyz

» Salvador Dalí’s 1870s Surreal Tarot Card Designs Being Released as a Complete Deck
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 11:25 am by PurpleSkyz

» Transit of Mercury as Seen from Space
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 11:07 am by PurpleSkyz

» ANTI-VAXXERS CRASH JIMMY KIMMEL SHOW TO WARN OF VACCINE DANGERS
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 10:42 am by PurpleSkyz

» #QTard Drama Theater - Late Breaking: Q is BACK BIGTIME! plus more
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 10:33 am by PurpleSkyz

» Earth's Magnetic North Pole Has Officially Moved
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 10:31 am by PurpleSkyz

» Brexit, Wokeness, & The Illusion Of Choice - David Icke
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 3:40 am by Em

» 14 typical excuses swindlers (Jerzy Babkowski) use to keep you on the hook, hoping your nightmare will end
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 2:18 am by RamblerNash

» Declassified Radar Reports of UFO's & Dec.4,1981 Declassified Incident With F4 and UFO
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 2:02 am by PurpleSkyz

» 11/11/2019 -- Large Meteor Explodes over Missouri USA -- Massive blast felt across region
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 1:59 am by PurpleSkyz

» NEW YOUTUBE TERMS: ACCOUNTS DEEMED NOT “COMMERCIALLY VIABLE” CAN BE DELETED
AI trained on old scientific papers makes discoveries humans missed EmptyYesterday at 1:49 am by PurpleSkyz

» WiFi, 5G and EMF pollution can cause PSYCHIATRIC effects in humans, plus spontaneous abortions, infertility and cellular DNA damage
AI trained on old scientific papers makes discoveries humans missed EmptyMon Nov 11, 2019 6:22 pm by PurpleSkyz

» Mercury set for rare transit of the Sun tomorrow
AI trained on old scientific papers makes discoveries humans missed EmptyMon Nov 11, 2019 6:17 pm by PurpleSkyz

» UFO News ~ UFO Fleet seen in Puebla,Mexico plus MORE
AI trained on old scientific papers makes discoveries humans missed EmptyMon Nov 11, 2019 6:03 pm by PurpleSkyz

CURRENT MOON

You are not connected. Please login or register

OUT OF MIND » PLANET AWARENESS » SCIENCE & TECHNOLOGY » AI trained on old scientific papers makes discoveries humans missed

AI trained on old scientific papers makes discoveries humans missed

Go down  Message [Page 1 of 1]

PurpleSkyz

PurpleSkyz
Admin
AI trained on old scientific papers makes discoveries humans missed Papers-1562727228646


AI trained on old scientific papers makes discoveries humans missed


Scientists used machine learning to reveal new scientific knowledge hidden in old research papers.
Using just the language in millions of old scientific papers, a machine learning algorithm was able to make completely new scientific discoveries.
In a study published in Nature on July 3, researchers from the Lawrence Berkeley National Laboratory used an algorithm called Word2Vec sift through scientific papers for connections humans had missed. Their algorithm then spit out predictions for possible thermoelectric materials, which convert heat to energy and are used in many heating and cooling applications.
Created in partnership with Peters Maxibon
How Do They Make Maxibons?
Aaron Gocs ventures into the Maxibon factory in search of perfection.
The algorithm didn’t know the definition of thermoelectric, though. It received no training in materials science. Using only word associations, the algorithm was able to provide candidates for future thermoelectric materials, some of which may be better than those we currently use.
“It can read any paper on material science, so can make connections that no scientists could,” researcher Anubhav Jain said. “Sometimes it does what a researcher would do; other times it makes these cross-discipline associations.”
To train the algorithm, the researchers assessed the language in 3.3 million abstracts related to material science, ending up with a vocabulary of about 500,000 words. They fed the abstracts to Word2vec, which used machine learning to analyze relationships between words.
“The way that this Word2vec algorithm works is that you train a neural network model to remove each word and predict what the words next to it will be,” Jain said. “By training a neural network on a word, you get representations of words that can actually confer knowledge.”
Using just the words found in scientific abstracts, the algorithm was able to understand concepts such as the periodic table and the chemical structure of molecules. The algorithm linked words that were found close together, creating vectors of related words that helped define concepts. In some cases, words were linked to thermoelectric concepts but had never been written about as thermoelectric in any abstract they surveyed. This gap in knowledge is hard to catch with a human eye, but easy for an algorithm to spot.
Advertisement
After showing its capacity to predict future materials, researchers took their work back in time, virtually. They scrapped recent data and tested the algorithm on old papers, seeing if it could predict scientific discoveries before they happened. Once again, the algorithm worked.
In one experiment, researchers analyzed only papers published before 2009 and were able to predict one of the best modern-day thermoelectric materials four years before it was discovered in 2012.
This new application of machine learning goes beyond materials science. Because it’s not trained on a specific scientific dataset, you could easily apply it to other disciplines, retraining it on literature of whatever subject you wanted. Vahe Tshitoyan, the lead author on the study, says other researchers have already reached out, wanting to learn more.
“This algorithm is unsupervised and it builds its own connections,” Tshitoyan said. “You could use this for things like medical research or drug discovery. The information is out there. We just haven’t made these connections yet because you can’t read every article.”

https://nexusnewsfeed.com/article/science-futures/ai-trained-on-old-scientific-papers-makes-discoveries-humans-missed

Thanks to: https://nexusnewsfeed.com



  

Back to top  Message [Page 1 of 1]

Permissions in this forum:
You cannot reply to topics in this forum