Become a Client

Now, Computers Can Actually Think Like Humans

Bill Wasinger

Bill Wasinger is an award winning copywriter and consultant with over 25 years experience writing for print, broadcast, and digital media. He operates his own copy and design firm, Ph Communications, working with a variety of national and regional brands.

Now, Computers Can Actually Think Like Humans 2

We’ve all known someone with the “brain like a computer.” But now, thanks to IBM‘s new True North processor, the world has a computer chip that thinks like a human brain.

Billed as a “neurosynaptic computer chip” that parallels the human brain’s computing abilities and power efficiency, True North is designed to process its environment and react accordingly in real time. While not quite as expansive as a human brain, the chip, which features 5.4 billion transistors, 1 million programmable neurons and 256 million programmable synapses, still offers the potential to operate devices to perform such tasks as proactively monitoring oils spills, enforcing shipping lanes or issuing tidal alerts. On a more human scale, TrueNorth could help vision-impaired people safely navigate their environment, distinguish different voices in a meeting and create accurate transcripts from each speaker.

The difference is the synaptic capability of True North, which was developed with funding from DARPA, the U.S. Defense Advanced Research Projects Agency. With the capability to sense its environment, TrueNorth can make decisions much as a human or animal would without the complex computational requirements of a traditional processor. Physically, imagine that TrueNorth fits the power of a so-called supercomputer into a chip that fits in the palm of your hand.

On a broader scale, TrueNorth, which was recently featured on CNET, is a core element of a new cognitive computing program from IBM called SyNapse. SyNapse’s TrueNorth, which has the capability of 46 billion synaptic operations per second, while using about the same amount of power as a hearing aid, could potentially change the architecture of computing by eliminating the limits of the mathematics-based von Neumann architecture. That’s the same architecture that has been the core of most computers built since the dawn of the computer age. And, while its still in its research phase, that means the potential for an entirely new class of powerful mobile apps and computing devices.

To top it all off, an IBM official noted the company hopes to make the SyNapse TrueNorth ecosystem available to anyone, including universities, startups, business partners and customers as soon as possible. And, to support what it anticipates to be a wide array of new algorithms, the company designed TrueNorth chips with the ability to be seamlessly tiled to create vast, scalable neuromorphic systems. The ultimate goal, according to IBM, is the integration of 4,096 chips in a single rack with 4 billion neurons and 1 trillion synapses using roughly 4kW of power.

Finally, IBM reminds us that TrueNorth is merely a direction, not a destination. It’s up to the minds of developers, researchers and tech companies to determine where the “computer chip that thinks like the brain” goes from here.

Image credit: IBM

Video credit: GeoBeats News



Stay Ahead of the AI Curve

Discover the critical AI trends and applications that separate winners from losers in the future of business.

Sign up for the ‘AI Advantage’ newsletter:

Stay Ahead of the Machine Learning Curve

At Emerj, we have the largest audience of AI-focused business readers online - join other industry leaders and receive our latest AI research, trends analysis, and interviews sent to your inbox weekly.

Thanks for subscribing to the Emerj "AI Advantage" newsletter, check your email inbox for confirmation.