New discovery paves way for brain-like computers

Research has long strived to develop computers to work as energy efficiently as our brains. A study, conducted by researchers at the University of Gothenburg, succeeded for the first time in combining a memory function with a calculation function in the same component. This discovery paves the way for more efficient technologies, ranging from cell phones to self-driving cars.

In recent years, computers have been able to tackle advanced cognitive tasks, like recognizing language and images or displaying superhuman chess skills, largely thanks to artificial intelligence (AI). At the same time, the human brain is still unmatched in its ability to perform tasks efficiently and energy-efficiently.

“Finding new ways to perform computations that mimic the energy-efficient processes of the brain has been a major research goal for decades. Cognitive tasks, such as image and voice recognition, require significant computing power, and mobile applications, in particular, such as cell phones, drones and satellites, require energy-efficient solutions,” says Johan Åkerman, professor of applied spintronics at the University of Gothenburg.

Important breakthrough

Together with a research team from Tohoko University, Åkerman conducted a study that has now taken an important step towards achieving this goal. In the study, published today in the prestigious journal Nature Materials, the researchers succeeded for the first time in linking the two main advanced computing tools: oscillator networks and memristors.

Åkerman describes oscillators as oscillating circuits capable of performing calculations and comparable to human nerve cells. Memristors are programmable resistors that can also perform calculations and have built-in memory. This makes them comparable to memory cells. The integration of the two is a major step forward for researchers.

“This is an important breakthrough because we show that it is possible to combine a memory function with a computation function in the same component. These components work more like the energy-efficient neural networks of the brain, their allowing more brain-like computers to become important building blocks in the future.”

Enables energy-efficient technologies

According to Johan Åkerman, this discovery will enable faster, easier to use and less energy-intensive technologies in many areas. He believes it’s a huge advantage that the research team managed to produce the components in an extremely small footprint: hundreds of components fit into an area equivalent to a single bacterium. This can be especially important in small applications like mobile phones.

“More energy-efficient calculations could lead to new features in mobile phones. An example is digital assistants like Siri or Google. Today all processing is done by servers because the calculations require too much energy to the small size of a phone. If the calculations could instead be done locally, on the actual phone, they could be done faster and easier without the need to connect to servers.”

He notes self-driving cars and drones as other examples where more energy-efficient calculations could lead to developments.

“The more energy-efficient cognitive computations can be performed, the more applications become possible. This is why our study really has the potential to advance the field.”

About the research area Neuromorphic computing is a field related to AI that attempts to mimic neural networks in the brain. The research uses new algorithmic approaches that resemble the way the human brain integrates with the surrounding world to provide a capability close to human cognition.

Source of the story:

Material provided by University of Gothenburg. Original written by Ulrika Ernström. Note: Content may be edited for style and length.