This site may earn chapter commissions from the links on this page. Terms of use.

Neurons

IBM has announced an exciting first challenge for its upcoming TrueNorth computer chips, and then-called "neuromorphic" computers physically structured like the encephalon: Wait at a mass of data collected from real human being brains, and make sense of it. That sort of pattern finding is something conventional computers are bad at doing, but IBM hopes with new engineering science it volition be able to watch the human encephalon in real-fourth dimension — and potentially intervene.

Large, truly unsafe epileptic seizures are a result of large-calibration storms of electrical activity raging dorsum and forth between the two hemispheres of the brain. Doctors accept had a hard time finding reliable signatures of these storms that can be detected early enough to allow effective counter-measures, just neural networks are perfectly suited to finding such complex patterns. IBM is feeding its new, neurally inspired TrueNorth fries reams of electro-encepholagram (EEG) readings from epileptics in the promise that they can find patterns associated with major seizures. But the real potential lies in application — and the unique advantages of neuromorphic architecture.

IBM's TrueNorth chip, and a few friends, in an SMP setup

IBM's TrueNorth chip, and a few friends, in an SMP setup

IBM in one case networked regular digital computers together into a simulation of a homo brain. It had the full level of complexity, but ran about 1,500 times slower than the real matter. The researchers at IBM pointed out the real limiting factor is non computational ability, just electric power. Because if we took the regular digital algorithms used to run the boring simulation, and merely ran information technology 1,500 times faster, we would end upwards using something like 12 gigawatts of power to do so. If y'all don't feel similar ringing your lab in nuclear ability plants, you'll have to come up with something significantly amend.

Thankfully, we accept a design: the human encephalon. After all, a human being brain runs the complexity of a human brain in real fourth dimension, and information technology does then for as little equally xx watts, or enough to power a pocket-size lightbulb. IBM's neuromorphic chips, called TrueNorth, have a portion of that increase in energy efficiency.

Aria deus ex wearable

Your side by side vesture might accept a silicon brain ticking away within…

What that means is that the fries best suited to running data-mining lawmaking, those that are physically structured like a neural network, are besides the chips with the best applied ability to apply those programs in the real globe. Complex, ever-on data mining hardware could run down fifty-fifty an enormous battery in just a couple of hours using conventional hardware; with TrueNorth or a similar compages, it might be possible to stay on our bodies and keep learning all twenty-four hour period, or even all calendar week.

The ultimate goal is to utilize TrueNorth to detect seizures in real-fourth dimension through an implant or wearable solution. A fleck, power-efficient enough to last, could monitor and sift EEG readings from a wearer to identify an oncoming seizure. It can and so warning you via your smartphone or, hopefully, one-day contact medical services straight or even administer medication if needed.

Wearable tech needs either a power revolution, or a power efficiency revolution. If we're ever going to power real devices with electricity harvested from your clothes, for instance, nosotros're going to need fries that can run on such paltry amounts of power. Neuromorphic chips could be one such technology. Monitoring epilepsy is just the beginning of the applications.