Intel Building AI Chips 😀😀

Chip making company  Intel is in the middle of an experiment with a neuromorphic chip that attempts to resemble the way the human brain work. Imagine a situation where you are asked to guess the emotion of someone in a video clip. It will lead to neurons in your brain exchanging information in a flurry of electronic spikes. In a similar manner, researchers at Intel recently put a challenge to the prototype of their new chip. The chip, called Loihi, tried to solve the problem with thousands of spiking silicon neurons of its own. Like our brain’s neurons, they can adjust the connections between themselves to adapt to new tasks. The new chip consists of 128 computing cores and each core has 1,024 artificial neurons, giving the chip a total of more than 1,30,000 neurons and 130 million synaptic connections. The new design, which is named after a submarine volcano in Hawaii, still is far away from a human brain. The human brain is made up of more than 80 billion neurons. But it’s very different from a conventional processor. Based on the number of neurons, the Loihi chip is a little more complex than the simple lobster brain.

Deep learning software runs on CPUs, but inefficiently. CPUs are inherently general purpose devices. Maximum computing power required for deep learning is possible only with new kinds of special purpose chips. 

The holy grail is a new kind of chip tailor-made for deep learning. That's what Rao and Nervana are attempting. If they succeed, Intel too will bear the fruit. 

Rao sports an athlete's build in his T-shirt and blue jeans. A child of Indian immigrants, he grew up in a tiny eastern Kentucky town called Whitesburg. In the late 1970s, his father, a physicist turned physician, drove Rao and his brother to a Radio Shack in Hazard, 40 minutes away, where they wrote programs in Basic on floor-model computers. "We didn't have a computer at home yet," he says. 

After a rural childhood that mixed outdoor sports with Dungeons & Dragons and novels by Asimov, Heinlein and Tolkien, Rao attended Duke University. There, he was attracted to neural networks after learning how the human eye detected edges on visual objects. Edge detection at the time was a cutting-edge problem in computer vision, with a number of solutions being offered up, including neural networks. 

He cut his teeth on computer chips at Sun Microsystems in Silicon Valley. Still drawn by all things neural, he earned a Ph.D. at Brown University under neuroscience pioneer John Donoghue. He headed back West to chipmaker Qualcomm in San Diego, on a team conducting neural net research. 

Loihi is Intel’s latest effort to turn the current vogue for AI into a new growth engine for the company. Last year, Intel acquired two start-ups working on chips to power machine learning in the cloud and for computer vision. Two years ago, it spent $16.7 billion, its largest acquisition ever, to acquire Altera, which builds the programmable chips that Microsoft uses. Last year, the company paid a reported $408 million buying Nervana, a company that was exploring a chip just for executing neural networks. Now, led by the Nervana team, Intel is developing a dedicated chip for training and executing neural networks. Rival chipmaker Nvidia currently dominates the AI market with its graphics processors. Officially, the company’s position is that improvements in traditional chips will continue well into the next decade.

But Intel is not the first company to design a chip using pointers from neuroscience. Tech giant IBM built two generations of its own neuromorphic processor. But that chip, unlike Intel’s, can’t learn from incoming data. The company has struck deals with two labs to build research systems with its chip, but not announced broad commercial availability. Whether or not Intel’s neuromorphic chip experiment ever becomes successful, it’s worthy to note that the unveiling highlights Intel’s interest in moving beyond the traditional central processing unit (or CPU) market, where the company is a market leader. Intel controls more than 90% of the data-centre market, making it by far the largest seller of traditional chips.

Intel is competing not only with chipmakers like Nvidia and Qualcomm, but also with companies like Google and Microsoft. Google is designing the second generation of its chips. Later this year, the company said, any business or developer that is a customer of its Cloud-computing service will be able to use the new chips to run its software. With this new chip, the hope is that there will be devices that will handle more complex tasks without having the need to call back to distant data centres.