AI researchers develop 'Darwin,' a neuromorphic chip based on spiking neural networks

December 23, 2015
Chip and the demonstration board. Credit: ©Science China Press

Artificial neural networks (ANNs) are a type of information processing system based on mimicking the principles of biological brains, and have been broadly applied in application domains such as pattern recognition, automatic control, signal processing, decision support systems and artificial intelligence. Spiking neural networks (SNNs) are a type of biologically inspired ANN that perform information processing based on discrete time spikes. They are more biologically realistic than classic ANNs, and can potentially achieve a much better performance-power ratio. Recently, researchers from Zhejiang University and Hangzhou Dianzi University in Hangzhou, China successfully developed the Darwin Neural Processing Unit (NPU), a neuromorphic hardware co-processor based on spiking neural networks, fabricated by standard CMOS technology.

With the rapid development of the "Internet of Things" and intelligent hardware systems, intelligent devices are pervasive in today's society, providing many services and conveniences to people's lives. But they also raise challenges of running complex intelligent algorithms on small devices. Sponsored by the college of Computer science of Zhejiang University, the research group led by Dr. De Ma from Hangzhou Dianzi university and Dr. Xiaolei Zhu from Zhejiang university has developed a co-processor called Darwin. The Darwin NPU aims to provide hardware acceleration of intelligent algorithms for resource-constrained, low-power embedded devices. It has been fabricated through a standard 180nm CMOS process, supporting a maximum of 2048 neurons, more than 4 million synapses and 15 different possible synaptic delays. It is highly configurable, supporting reconfiguration of SNN topology and many parameters of neurons and synapses. Figure 1 shows photos of the die and the prototype development board, which supports input/output in the form of neural spike trains via USB port.

The successful development of Darwin demonstrates the feasibility of real-time execution of spiking in resource-constrained embedded systems. It supports flexible configuration of a multitude of parameters of the neural network; it can therefore be used to implement different functionalities as configured by the user. Its potential applications include intelligent hardware systems, robotics, brain-computer interfaces, and others. Since it uses spikes for information processing and transmission, similar to biological neural networks, it may be suitable for analysis and processing of biological spiking neural signals, and building brain-computer interface systems by interfacing with animal or human brains. As a prototype application in brain-computer interfaces, Figure 2 describes an example application of recognizing the user's motor imagery intention via real-time decoding of EEG signals, i.e., whether the user is thinking of left or right, and using that information to control the movement direction of a basketball in the virtual environment. Different from conventional EEG signal analysis algorithms, the input and output to Darwin are both neural spikes: The input consists of spike trains that encode EEG signals; after processing by the neural network, the output neuron with the highest firing rate is chosen as the classification result.

EEG signal recognition. Credit: ©Science China Press

Explore further: Artificial brains learn to adapt

More information: "Darwin: a Neuromorphic Hardware Co-Processor based on Spiking Neural Networks",to be published in SCIENCE CHINA Information Sciences, 2016 No.2 issue:

Related Stories

Artificial brains learn to adapt

May 16, 2014

For every thought or behavior, the brain erupts in a riot of activity, as thousands of cells communicate via electrical and chemical signals. Each nerve cell influences others within an intricate, interconnected neural network. ...

Chips that mimic the brain

July 22, 2013

No computer works as efficiently as the human brain – so much so that building an artificial brain is the goal of many scientists. Neuroinformatics researchers from the University of Zurich and ETH Zurich have now made ...

Synapses need only few bits

September 22, 2015

Deep learning is possibly the most exciting branch of contemporary machine learning. Complex image analysis, speech recognition and self-driving cars are just a few popular examples of a multitude of new applications where ...

A network of artificial neurons learns to use human language

November 11, 2015

A group of researchers from the University of Sassari (Italy) and the University of Plymouth (UK) has developed a cognitive model, made up of two million interconnected artificial neurons, able to learn to communicate using ...

Brain process takes paper shape

February 12, 2014

A paper-based device that mimics the electrochemical signalling in the human brain has been created by a group of researchers from China.

Recommended for you

Microsoft aims at Apple with high-end PCs, 3D software

October 26, 2016

Microsoft launched a new consumer offensive Wednesday, unveiling a high-end computer that challenges the Apple iMac along with an updated Windows operating system that showcases three-dimensional content and "mixed reality."

Making it easier to collaborate on code

October 26, 2016

Git is an open-source system with a polarizing reputation among programmers. It's a powerful tool to help developers track changes to code, but many view it as prohibitively difficult to use.

Dutch unveil giant vacuum to clean outside air

October 25, 2016

Dutch inventors Tuesday unveiled what they called the world's first giant outside air vacuum cleaner—a large purifying system intended to filter out toxic tiny particles from the atmosphere surrounding the machine.


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.