ByRutledge Moeller 2019-12-27 1898
Researchers created a set of data that collected nearly 5000 molecules identified by perfumers and labeled them with descriptions such as "butter", "tropics" and "weeds". The team used about 2/3 of the data to train its artificial intelligence. The researchers then used the remaining odors to test artificial intelligence, and the results showed that these algorithms could predict molecular odors based on their structure.
But the foreign media have put forward several points for attention, and it is these problems that make olfactory research so difficult. First of all, two people may describe the same smell in different ways, such as "wood" or "earthy smell". Second, sometimes molecules have the same atoms and molecular bonds, and they are mirrored but have a completely different smell. This phenomenon is called "chiral molecular symmetry", such as champagne and mint. In addition, when you start mixing odors, things get more complicated.
Google researchers believe that training artificial intelligence to associate specific molecules with odors may greatly affect chemical research; human understanding of nutrition; sensory neuroscience and how we synthesize spices.
|You may also want to read:|
|Does the HUAWEI FreeBuds 3 Work Well With iPhone?|
|Realme Buds Air VS JBL C100TWS: Which is More Worth Buying?|
|Does the i12 TWS Earbuds Work with Android Phone?|
|How to Charge your AirPods Pro and Check the AirPods Pro Battery State?|
● Over 300,000 products
● 20 different categories
● 15 local warehosues
● Multiple top brands
● Global payment options: Visa, MasterCard, American Express
● PayPal, Western Union and bank transfer are accepted
● Boleto Bancario via Ebanx (for Brazil)
● Unregistered air mail
● Registered air mail
● Priority line
● Expedited shipping
● 45 day money back guarantee
● 365 day free repair warranty
● 7 day Dead on Arrival guarantee (DOA)