Scientists say a simple artificial neural circuit is a small but important step for artificial intelligence. The circuit of about 100 artificial synapses performed a simple version of a typical human task: image classification.
With time and further progress, the circuitry may eventually be expanded and scaled to approach something like the human brain, which has 1015 (one quadrillion) synaptic connections.
For all its errors and potential for faultiness, the human brain remains a model of computational power and efficiency for engineers. The brain can accomplish certain functions much faster and efficiently than computers.
For example, as you read this, your brain is making countless split-second decisions about the letters and symbols you see, classifying their shapes and relative positions to each other and deriving different levels of meaning through many channels of context, in as little time as it takes you to scan over this print. Change the font, or even the orientation of the letters, and it’s likely you would still be able to read this and derive the same meaning.
The new circuit was able to successfully classify three letters (“z”, “v,” and “n”) by their images, each letter stylized in different ways or saturated with noise. In a process similar to how we humans pick our friends out from a crowd, the simple neural circuitry was able to correctly classify the simple images.
“While the circuit was very small compared to practical networks, it is big enough to prove the concept of practicality,” says Farnood Merrikh-Bayat, a researcher at the University of California, Santa Barbara.
THE KEY COMPONENT: A ‘MEMRISTOR’
Key to this technology is the memristor (a combination of “memory” and “resistor”), an electronic component whose resistance changes depending on the direction of the flow of the electrical charge. Unlike conventional transistors, which rely on the drift and diffusion of electrons and their holes through semiconducting material, memristor operation is based on ionic movement, similar to the way human neural cells generate neural electrical signals.
“The memory state is stored as a specific concentration profile of defects that can be moved back and forth within the memristor,” says Dmitri Strukov, a professor of electrical and computer engineering.
The ionic memory mechanism brings several advantages over purely electron-based memories, which makes it very attractive for artificial neural network implementation, he added.
“For example, many different configurations of ionic profiles result in a continuum of memory states and hence analog memory functionality,” he says. “Ions are also much heavier than electrons and do not tunnel easily, which permits aggressive scaling of memristors without sacrificing analog properties.”
INSPIRED BY THE BRAIN
This is where analog memory trumps digital memory. In order to create the same human brain-type functionality with conventional technology, the resulting device would have to be enormous—loaded with multitudes of transistors that would require far more energy.
“Classical computers will always find an ineluctable limit to efficient brain-like computation in their very architecture,” says lead researcher Mirko Prezioso. “This memristor-based technology relies on a completely different way inspired by biological brain to carry on computation.”
To approach the functionality of the human brain, however, many more memristors would be required to build more complex neural networks.
The next step would be to integrate a memristor neural network with conventional semiconductor technology, which will enable more complex demonstrations and allow this early artificial brain to do more complicated and nuanced things.
Konstantin Likharev from Stony Brook University also conducted research for this project. The researchers’ findings are published in the journal Nature.
No comments:
Post a Comment