Eye on AI - March 27th, 2020
Welcome to Aigora's "Eye on AI" series, where we round up exciting news at the intersection of consumer science and artificial intelligence!
This week, we move away from COVID-19 to look at some exciting new progress in the functionality of the “e-nose” technology, which mimics the mammalian brain, while including a news round-up of how COVID-19 and tech are interacting. Stay safe, everyone!
New AI Algorithm Uses Rodent Study to Passes Smell Test Nearly 100%
We begin with news in the artificial smelling arena, a topic we touched on when it was still in its infancy a while back. Smell AI accelerated this week when a partnership was announced between researchers who created an algorithm mimicking the olfactory bulb in the mammalian brain and Intel. MIT Tech Review reporter Robby Bermman, in her article “A new AI passes the smell test almost 100% of the time,” explains:
“The brain's olfactory bulb has hundreds of receptors tracking odors all the time, and yet somehow keeps everything straight,” writes Bermann. “A scientist at Cornell University working with a researcher at Intel has just created an AI algorithm trained to recognize 10 scents by mimicking the mammalian olfactory bulb (MOB). Give the algorithm a computer chip to run on and it can learn to identify new odors.”
The work is the result of over a decade of studying olfactory bulb circuitry, which helps mammals distinguish smell, in rodents, with particular attention paid to things the olfactory bulb can do in animals that machines can't. Through the years, the algorithm was trained to identify ten prominent chemical smells, found in things like explosives, and of those ten, eight were correctly identified by the algorithm 100% of the time, with two at 90%. The icing on the algorithm’s proverbial cake is its partnership with a specialized chip by Intel, which enables it to expand far beyond its original capabilities.
Intel’s Loihi Chip Could Expand Algorithm’s Potential to Other Senses
To conclude, let’s take a look at the specialized chip used to host the algorithm, produced by scientists at Intel, called Loihi.
“The chip is something of a wonder all by itself,” continues Bermann. “It's designed to perform neuromorphic computing inspired by the brain, sporting some 130,000 silicon ‘neurons.’ Like our own neurons, each can fire independently of the others, sending pulsed signals to its neighbors, changing their electrical states. In addition, Loihi can accept inputs from a variety of physical sensors, such as the metal-oxide chemical sensors that Cleland and Imam (the scientists responsible for the algorithm) used, allowing the entire structure to simulate the natural learning process that occurs when the mammalian brain is fed various sensory inputs.”
In conjunction with the algorithm’s advances, Intel scientists on Monday released an article that proposed a new neuromorphic chip design that would mimic the structure and capabilities of the olfactory bulb at the heart of the algorithm.
“The researchers worked with olfactory neurophysiologists who study the brains of animals as they smell,” writes MIT Tech Review reporter Karen Hao. “They designed an electrical circuit, based on the neural circuits that activate when their brains process an odor, that could be carved onto a silicon chip. They also designed an algorithm that mirrors the behavior of the electrical signals that pulse through the circuit. When they trained the algorithm on the chip using an existing data set of 10 “smells”—characterized by their measurements from 72 different chemical sensors—it was able to accurately distinguish between them with far fewer training samples than a conventional chip.”
The potential of this algorithm, and other algorithms like it, in conjunction with Intel’s new chip design, may be far-reaching, as the new chip allows the algorithm to process sense data much like the brain would, though with expanded storage potential.
“Moving forward, the research team plans to improve the design of its neuromorphic chip and apply it to other functions of the brain beyond smell,” continues Hao. “.... the team will likely turn its attention to vision or touch next but has longer-term ambitions to tackle more complex processes. ‘Our sensing mechanisms are the natural place to start because these are well understood,’ one researcher noted. ‘But in a sense we’re working our way in and into the brain, up to the higher-order thought processes that happen.’”
COVID-19 and tech news:
That's it for now. If you'd like to receive email updates from Aigora, including weekly video recaps of our blog activity, click on the button below to join our email list. Thanks for stopping by!