The world of data storage is constantly pushing the limits of what technology can accommodate. With large-capacity hard drives and devices that are constantly getting smaller, scientists, engineers and developers are constantly on the lookout for the next big breakthrough. They may have found it in the form of a next-gen supercomputer that is no larger than the average postage stamp.
Known as TrueNorth, the chip was pioneered through a collaborative effort that was led by IBM. The project is actually based on neurosynaptic cores, each of which contains 256 neurons. Such technology was introduced by IBM back in 2011.
A recent blog post by IBM Stated: "Six years ago, IBM and our university partners embarked on a quest—to build a brain-inspired machine—that at the time appeared impossible. Today, in an article published in Science, we deliver on the DARPA SyNAPSE metric of a one million neuron brain-inspired processor. The chip consumes merely 70 milliwatts, and is capable of 46 billion synaptic operations per second, per watt–literally a synaptic supercomputer in your palm."
When operating, each neuron contained within the chip is capable of connecting to hundreds of other neurons. This provides it with immense computational power, including the ability to identify and scrutinize individual features within a visual image. Moreover, the compact size of the chip allows it to achieve such advanced calculations with relatively little power consumption.
TrueNorth and Data Storage
Experts within the IT industry are enthusiastic about the future of TrueNorth, but they're hesitant to fully embrace the technology. Some see potential uses in the medical field, law enforcement, national defense and even in disaster rescue and recovery efforts. Others are interested in this technology for its potential application in the niche of data storage.
IBM's blog post continued to say: "The architecture can solve a wide class of problems from vision, audition, and multi-sensory fusion, and has the potential to revolutionize the computer industry by integrating brain-like capability into devices where computation is constrained by power and speed. These systems can efficiently process high-dimensional, noisy sensory data in real time, while consuming orders of magnitude less power than conventional computer architectures."
Faster speeds and greater efficiency of these systems will certainly lend themselves well to the growing issue of big data around the world. While we've seen a proliferation of large-capacity drives and devices as of late, breakthroughs like this are bound to push the limits of modern storage technology and the capacities they can achieve.
The United States Air Force is already using the TrueNorth chip as part of a system to help spot and identify ground-based threats from the air. Using highly advanced image-processing software, the Air Force relies on a public dataset known as MSTAR to match up their real-time scans with the images of tanks and other vehicles that are stored on their hard drives and devices.
For more information on IBM, including the latest details of their research into the TrueNorth chip, please visit their official website at www.research.ibm.com.
Did We Invent The Computer Wrong? Using "Neurons" instead of Traditional Switches
No comments yet. Sign in to add the first!