Skip to main content

Intel is using A.I. to build smell-o-vision chips

While smell-o-vision may be a long way from being ready for your PC, Intel is partnering with Cornell University to bring it closer to reality. Intel’s Loihi neuromorphic research chip, a a powerful electronic nose with a wide range of applications, can recognize dangerous chemicals in the air.

“In the future, portable electronic nose systems with neuromorphic chips could be used by doctors to diagnose diseases, by airport security to detect weapons and explosives, by police and border control to more easily find and seize narcotics, and even to create more effective at home smoke and carbon monoxide detectors,” Intel said in a press statement.

Recommended Videos

With machine learning, Loihi can recognize hazardous chemicals “in the presence of significant noise and occlusion,” Intel said, suggesting the chip can be used in the real world where smells — such as perfumes, food, and other odors — are often found in the same area as a harmful chemical. Machine learning trained Loihi to learn and identify each hazardous odor with just a single sample, and learning a new smell didn’t disrupt previously learned scents.

Intel Labs senior research scientist Nabil Imam who worked on the Loihi development team used the same computational principles of scent analysis as biological brains in humans and animals. The company worked with Cornell to analyze the brain’s electrical activity when animals smell odors, while Intel Labs scientists derived a set of algorithms to configure them to neuromorphic silicon.

There’s still plenty of work to be done on electronic noses. Like image detection in machine learning, olfactory learning requires similar smells to be categorized. Fruits with similar odors, for example, can be difficult for neuromorphic systems like to Loihi to identify.

“Imam and team took a dataset consisting of the activity of 72 chemical sensors in response to 10 gaseous substances (odors) circulating within a wind tunnel,” Intel detailed. “The sensor responses to the individual scents were transmitted to Loihi, where silicon circuits mimicked the circuitry of the brain underlying the sense of smell. The chip rapidly learned neural representations of each of the 10 smells, including acetone, ammonia and methane, and identified them even in the presence of strong background interferents.”

Intel claims Loihi can learn 10 different odors right now. In the future, robots equipped with electronic noses might be used to monitor the environment, and doctors could use these computerized olfactory systems for medical diagnosis in instances where diseases emit particular odors.

Chuong Nguyen
Silicon Valley-based technology reporter and Giants baseball fan who splits his time between Northern California and Southern…
Perplexity to introduce sneaky ads alongside its AI answers
Someone holding an iPhone 14 Pro, with Perplexity AI running on it.

It was only a matter of time. "Answer engine" startup Perplexity AI announced on Wednesday that it will begin experimenting with inserting advertisements into its chatbot responses starting next week.

Rather than a standard ad you might be familiar with, however, the platform will instead start showing ads to users in the U.S. in the form of "sponsored follow-up questions and paid media positioned to the side of an answer," from the company's advertising partners. Those include Indeed, Whole Foods, Universal McCann, and PMG.

Read more
Is AI already plateauing? New reporting suggests GPT-5 may be in trouble
A person sits in front of a laptop. On the laptop screen is the home page for OpenAI's ChatGPT artificial intelligence chatbot.

OpenAI's next-generation Orion model of ChatGPT, which is both rumored and denied to be arriving by the end of the year, may not be all it's been hyped to be once it arrives, according to a new report from The Information.

Citing anonymous OpenAI employees, the report claims the Orion model has shown a "far smaller" improvement over its GPT-4 predecessor than GPT-4 showed over GPT-3. Those sources also note that Orion "isn’t reliably better than its predecessor [GPT-4] in handling certain tasks," specifically coding applications, though the new model is notably stronger at general language capabilities, such as summarizing documents or generating emails.

Read more
An AI robot’s painting was just auctioned for more than $1 million
Ai-Da beside its painting of Alan Turing.

A painting of British computer scientist and codebreaker Alan Turing that was created by an AI-powered robot has fetched $1.08 million at auction.

The astonishing amount marks a record sale for a piece of art created by a humanoid robot, and is sure to provoke discussion about the effect AI is having on art and how it is created.

Read more