Skip to main content

IBM unveils neural computer as powerful as a frog's brain

Researchers at IBM claim to have developed a computer chip that has the same power as a frog's brain. The chip uses a 4,096-core processor that simulates the working of a million biological neurons.

To test-drive the impressively ambitious tech, IBM stuffed 16 of the TrueNorth chips onto one circuit board to model "sixteen million programmable neurons and four billion programmable synapses," which equals the 16 million neurons in the brain of your typical frog.

Read more: Supercomputer takes 40 mins to calculate a single second of human brain activity

The neural network project is funded by the Defense Advanced Research Projects Agency (DARPA), an agency of the United States Department of Defense responsible for the development of new technologies for use by the military.

The chip is built on what's known as non-von Neumann computer architecture. To rewind, the Von Neumann architecture, also known as the Von Neumann model and Princeton architecture, is a computer architecture based on that described in 1945 by the mathematician and physicist John von Neumann. This describes a design architecture for an electronic digital computer with parts consisting of a processing unit containing an arithmetic logic unit and processor registers, a control unit containing an instruction register and program counter, a memory to store both data and instructions, external mass storage, and input and output mechanisms.

Related: Will we ever manage to compute the human brain?

The new chip (like Apple's A7 chip in the iPhone 5S, by the way), runs using Samsung's 28nm process technology. This allows the enormous 5.4 billion transistor chip to have an on-chip network of 4096 neurosynaptic cores, but to sip power at only 70mW of consumption during real-time operation. This allows it to reach the record-breaking level of 46 billion synaptic operations per second per watt.

"IBM has broken new ground in the field of brain-inspired computers, in terms of a radically new architecture, unprecedented scale, unparalleled power/area/speed efficiency, boundless scalability, and innovative design techniques," said Dr. Dharmendra S. Modha, IBM Fellow and IBM Chief Scientist, Brain-Inspired Computing, IBM Research.

"We foresee new generations of information technology systems – that complement today's von Neumann machines – powered by an evolving ecosystem of systems, software, and services."

These brain-inspired chips could transform mobility, via sensory and intelligent applications that can fit in the palm of your hand but without the need for Wi-Fi."

This January it was announced that one of the world's largest supercomputers had accurately mapped one second's worth of activity in a human brain, in what researchers claim is the most accurate simulation to date.

Scientists in Japan simulated one per cent of the neuronal network in the brain using the K computer, the fourth most powerful supercomputer in the world.

Related: MIT Researchers Develop Chip That Mimics Human Brain