Artificial Intelligence
Researchers at Tohoku University have, for the first time, successfully demonstrated the basic operation of spintronics-based artificial intelligence.
Researchers at Tohoku University in Japan have, for the first time, successfully demonstrated the basic operation of spintronics-based artificial intelligence. The research has been published online in the journal Applied Physics Express.
Typical artificial intelligence systems today utilize conventional framework of semiconductor-based integrated circuit technology. Tasks such as image recognition and weather prediction, already make practical applications of this approach. However, conventional frameworks lack the compactness and low-power feature of the human brain.
To overcome this challenge, the implementation of a single solid-state device that plays the role of a synapse is highly promising.
The Tohoku University research group of Professor Hideo Ohno, Professor Shigeo Sato, Professor Yoshihiko Horio, Associate Professor Shunsuke Fukami and Assistant Professor Hisanao Akima developed an artificial neural network in which their recently-developed spintronic devices, comprising micro-scale magnetic material, are employed.
Related articles
In the image above, an optical photograph of a spintronic device that serves as artificial synapse. On the right hand side, is a photograph of the spintronic device array mounted on a ceramic package.
The spintronic device developed by the researchers is capable of memorizing arbitral values between 0 and 1 in an analogue manner unlike the conventional magnetic devices, and thus perform the learning function, which is served by synapses in the brain.
Using the network, the researchers examined an associative memory operation, which is not readily executed by conventional computers. Through multiple trials, they confirmed that the spintronic device has a learning ability with which the developed artificial neural network can successfully associate memorized patterns from their input noisy versions. This, say the researchers works just like a human brain does.
The proof-of-concept demonstration in this research is expected to open new horizons in artificial intelligence technology—where technology of compact size, and simultaneous fast-processing capabilities are made available in an ultralow-power consumption framework.
These features should enable the artificial intelligence to be used in a broad range of societal applications such as image/voice recognition, wearable terminals, sensor networks and nursing-care robots claim the researchers.
0 comments:
Post a Comment