SpiNNaker2 spiking neural network project gets €2.5 million

Technology News | February 27, 2023

By Peter Clarke

SpiNNcloud Systems GmbH (Dresden, Germany), a spin off from the Technische Universität Dresden, has been awarded €2.5 million for a project called SpiNNode: SpiNNaker2 on the edge.

The money has been awarded by the European Innovation Council (EIC) as part of its package of funding for deeptech startups.

The EIC has selected 27 projects out of 289 proposals submitted to the transition grant program to receive a total of €79.3 million in EU funding. This program aims to transform research results from European research projects into commercially viable businesses.

The support for SpiNNcloud Systems will enble it to start delivering its first artificial intelligence systems in 2024, the company said. SpiNNaker2 is a neural networking chip that is based on a spiking as a means of communications between neurons; a method that is modelled on the human brain. Each chip includes more than 100 ARM cores and has also made use of numerous hardware techniques to minimize energy consumption. Tens of thousands of SpiNNaker2 chips are expected to be deployed in an AI supercomputer.

“SpiNNaker2 is a bio-inspired supercomputer which was developed at my Chair in collaboration with Professor Steve Furber’s research group at the University of Manchester as part of the Human Brain Project’s European flagship. It is the world’s largest and most energy-efficient supercomputer for real-time artificial intelligence,” said Professor Christian Mayr.

Professor Angela Rösen-Wolff, vice-rector for research at TU Dresden added: “The EIC grant will enable SpiNNaker2 to expand to mobile applications, such as human-machine interaction in our CeTI Cluster of Excellence, and to be tested in realistic industrial environments.”

Christian Eichhorn, Co-CEO of SpiNNcloud Systems, said: “AI, such as ChatGPT, is now entering our everyday lives and, therefore, represents a revolution comparable to that of the internet. Training this AI model consumes as much electricity as 3,000 households use in a month. It is not yet possible to predict the scale of future electricity consumption resulting from the use of AI. We are working on the most energy-efficient computing hardware for large-scale applications, as this will be key to significantly reducing the carbon footprint of AI.”

Hector Gonzalez, Co-CEO von SpiNNcloud Systems, added: “Our inspiration is the human brain, which only requires 30 watts to tackle the most complex tasks. The future of computing technology must be inspired by the brain.”