Neuromorphic Computing Analyzes Brain Waves in Real-Time

Researchers at University of Zurich, ETH Zurich, and University Hospital Zurich have developed a compact, energy-efficient device made from artificial neurons. It is capable of decoding brain waves in biological brains. The chip uses data recorded from the brain waves of epilepsy patients to identify which regions of the brain cause epileptic seizures. This opens up new perspectives for treatment.

"Our design allows us to recognize spatiotemporal patterns in biological signals in real time," says research leader Giacomo Indiveri in a press release issued by University of Zurich.

A paper is published in Nature Communications. It describes a chip based on neuromorphic technology that reliably and accurately recognizes complex biosignals. Neuromorphic technology, based on brain-inspired computer system architectures, is a promising new approach that bridges the gap between artificial and natural intelligence.

Artificial Intelligence (AI) algorithms have produced spectacular results. However, the hardware used to run AI algorithms still requires too much processing power. Therefore, AI systems cannot yet compete with an actual brain when it comes to processing sensory information or interactions with the environment in real time.

The researchers have designed and built a hardware and software neuromorphic system. It includes a neural recording headstage and a neural network to analyze the resulting brainwaves.

The system is compact and embeddable. And it's suitable for applications such as real-time recording and processing of brain waves, which cannot rely on cloud computing solutions.The paper reports that the researchers used this technology to successfully detect promising biomarkers for identifying the brain tissue that causes epileptic seizures.

The neural network software runs in a fingernail-sized piece of hardware that receives neural signals by means of electrodes. Unlike conventional computers, it is massively energy efficient. This makes calculations with a very high temporal resolution possible, without relying on the internet or cloud computing.

"A portable or implantable chip such as this could identify periods with a higher or lower rate of incidence of seizures, which would enable us to deliver personalized medicine,” says researcher Johannes Sarnthein.

The researchers are now planning to use their findings to create an electronic system that reliably recognizes and monitors epilectic seizures in real-time. When used as an additional diagnostic tool in operating theaters, the system could improve the outcome of neurosurgical interventions.

The long-term target of this research is to develop a device for monitoring epilepsy that could be used outside of the hospital. That would make it possible to analyze signals from a large number of electrodes over several weeks or months. "We want to integrate low-energy, wireless data communications in the design - to connect it to a cellphone, for example," says Indiveri.

The press release and the research paper don’t speculate on possible applications of this new technology to general purpose brain-computer interfaces. But the idea jumps to mind.