New, Superfast Energy Efficient Computer Chips are Modeled on the Human Brain

Want to develop a faster microchip? Then basing it on the human brain is a good place to start. Scientists have created a more energy-efficient circuit board that's 9,000 times faster than usual by modeling it on the human brain.

The human brain is an impressive organ. For example, a mouse cortex operates 9,000 times faster than a personal computer simulation of its functions. Not only is a PC slower, though; it also consumes more energy. It takes 40,000 times more power to run when compared to the brain.

"From a pure energy perspective, the brain is hard to match," said Kwabena Boahen, one of the researchers, in a news release. Needless to say, mimicking the brain could potentially give computers the leg up that they need to be more efficient.

In this case, the researchers created Neurogrid, a circuit board consisting of 16 custom-designed "Neurocore" chips. Together, these chips can simulate 1 million neurons and billions of synaptic connections. The chips were also designed with power efficiency in mind, enabling certain synapses to share hardware circuits. Neurogrid is about the size of an iPad and can simulate orders of magnitude more neurons and synapses than other brain mimics on the power it takes to run a tablet computer.

While this new device is a huge leap forward for computing, there's still a lot of work to do. Each of the Neurogrid circuit boards cost about $40,000. Not only that, but it's difficult to operate.

"Right now, you have to know how the brain works to program one of these," said Boahen in a news release. "We want to create a neurocompiler so that you would not need to know anything about synapses and neurons to be able to use one of these."

The latest creation could eventually pave the way for faster, more energy-efficient computers based on the human brain. Not only that, but a chip as fast and efficient as the human brain could potentially drive prosthetic limbs with the speed and complexity of our own actions. It's a good step forward for the advancement of computing.

The findings are published in the journal Proceedings of the IEEE.