- How to stream Alistair Overeem vs. Jairzinho Rozenstruik 1 Month Ago
- Amazon sends customers condoms and soap instead of Nintendo Switch 1 Month Ago
- How to live stream Jermall Charlo vs. Dennis Hogan Today 8:00 AM
- Apple TV’s ‘Truth Be Told’ is a criminally dull drama Today 6:00 AM
- Thousands of Uber users have reported sexual assaults, company says Friday 5:40 PM
- ‘Astronomy Club’ reformats the sketch show Friday 4:58 PM
- Trump is concerned America’s toilets too weak Friday 3:53 PM
- Twitter users claim Billie Eilish is ‘over’ because she didn’t like Lady Gaga’s meat dress Friday 2:53 PM
- Nikki Haley says the Confederate flag was fine until Dylann Roof ‘hijacked’ it Friday 2:49 PM
- How emotional labor discourse spawned multiple memes Friday 2:22 PM
- Video of YouTuber Onision threatening ex-girlfriend resurfaces Friday 2:03 PM
- Marianne Williamson embraces anti-vax stance on Facebook Friday 1:58 PM
- Peloton Husband is worried memes will have ‘repercussions’ for his career Friday 1:55 PM
- ‘The Mandalorian’ stumbles as it returns to a familiar planet Friday 1:47 PM
- The best app controlled Christmas lights for the holidays Friday 1:04 PM
Google is in the process of teaching an artificial intelligence (AI) to recognize smells based on their chemical structure.
In a paper released by the Google Brain Team this week, researchers outlined how they used what is known as a graph neural network, or GNN, to analyze the molecules in certain smells.
The researchers enlisted the help of expert perfumers and matched close to 5,000 molecules to specific identifiers such as “jasmine” or “sweet.”
The team used roughly two-thirds of the molecule dataset to train their neural network and then attempted to see if it could correctly describe the rest.
Incredibly, in what appears to be a major breakthrough, the neural network accurately categorized the remaining molecules.
Alex Wiltschko, who led the Google project, told Wired that he believes the research has “pushed the field forward.”
Despite the significant discovery and breakthrough, Wiltschko noted that the research comes with its caveats.
Firstly, a specific smell can be described in numerous ways depending on who you ask. One person may describe a scent as “woody” while another say it is actually “earthy.”
Wiltschko also pointed to the issue of Chiral pairs, which share the same atoms and bonds but are mirror images of each other. Chiral pairs are classified as the same by the neural network despite having totally different smells. So while the neural network might be right about something on a molecular level, it might get the scent wrong.
“We know we have chiral pairs in our data set, and we know we cannot possibly be predicting them correctly,” Wiltschko said.
Proper categorization also becomes difficult once smells are combined as well. But Wiltschko and his team appear to be up to the challenge to continue pushing the field forward.
- Artificial Intelligence is a marketer’s dream–will it hurt consumer choice?
- Artificial intelligence and the death of decision-making
- Trump executive order prioritizes funding for artificial intelligence
Mikael Thalen is a tech and security reporter based in Seattle, covering social media, data breaches, hackers, and more.