Page 24

EETE DEC 2015

machine learning Startup wants to be the ARM of neuromorphic cores By A Peter Clarke recently formed startup company BrainChip Inc. (Aliso Viejo, Calif.) wants to bring the advantages of hardwarebased neuromorphic processing – mainly low power consumption – to market by partnering with chip companies in such areas as mobile phones and the Internet of Things. The company has told EE Times Europe that it has developed its first core, the SNAP-64 processor, and plans to follow an “ARM-like” business model. In other words it will license its technology and circuit designs for use by semiconductor companies and will receive a royalty typically a percentage of the chip price on each chip sold that includes its intellectual property. The company’s technology, based on spiking neural networks, has been in development for many years although the company was founded in December 2013. It is largely the result of several years’ work by Peter Van Der Made, chief technology officer and interim CEO. Spiking neural networks are modelled much more closely on human brain activity that conventional weighted neural networks in that they transmit information by a series of pulses from neuron to neuron. Unusually for a startup BrainChip is already a public company having been supported and funded through a reverse takeover by a former Australian minerals exploration company, Aziana Ltd. Earlier this year Aziana acquired BrainChip Inc and changed the name to Brain Chip Holdings Ltd. but brings with it cash resources and a listing on the Australian Securities Exchange (ASX). BrainChip is not the first company to seek to implement neural networks in hardware. IBM has announced its TrueNorth chip, Qualcomm’s Zeroth processor core is included on its Snapdragon 820 system chip and Intel has included a neural network core for pattern classification inside its Quark SE chip courtesy of a licensing deal. NeuroMem Inc. (Petaluma, Calif.) offers the technology for license and in chip form. However, BrainChip claims its model of brain activity is superior and its performance faster because of the fact that it uses a spiking model of the neural network information transfer. That said, Qualcomm claims its Zeroth processor core has also evolved from focusing on biologically realistic spiking neural networks to also include artificial neural networks for on-device deep learning. BrainChip also claims that it is the first company to hold a granted patent on digital spiking neural network technology (see Patent number US 8,250,011 Autonomous learning dynamic artificial neural computing device and brain inspired system) Neil Rinaldi, former CEO of Aziana and now non-executive director of BrainChip Holdings Ltd, told EE Times Europe that BrainChip Inc. has been drawing up protection of its intellectual property. The company has five additional patents pending and a further 76 patents in the process of being filed. The SNAP-64 has been implemented in FPGA and the company is looking to implement the core in a leading-edge manufacturing process at a foundry. “The expectation is that many licensees will want to implement the core as co-processor in a system chip. On-chip it can be configured to meet a wide variety of applications.” BrainChip is also prepared to engage with more advanced customers who wish to adapt the overall architecture for specific applications. “We have engaged discussions with a number of companies in the mobile phone and IoT sectors,” said Rinaldi. Other applications include robotics and autonomous learning machines used in exploration and unmanned vehicles, speech recognition, extraction of speech and sound from a noisy background and visual image recognition. The SNAP-64 has been designed and run in software simulation as well as implemented on an FPGA but technical questions remain as to the complexity it represents in terms of neuron and synapse connections, the resolution of the stimulus and spiking signal resolution, and the interface provided between the SNAP-64 and conventional Von Neumann processors. The company is looking to appoint a permanent CEO. Audi to field test automated parking, V2X near Boston ABy Christoph Hammerschmidt udi and the city of Somerville (Massachussetts, USA) have agreed to jointly develop strategies for urban driving. With technologies such swarm intelligence, vehicle-to-infrastructure communications (V2X) and piloted driving, the partners plan to develop concepts for future mobility in cities. During the Smart City Expo World Congress in Barcelona (Spain), Somerville city mayor Joseph A. Curtone and Audi CEO Rupert Stadler signed a Memorandum of Understanding that provides a close collaboration in developing a new mobility strategy for the US city. “The intelligent car can unfold its enormous potential only in a smart city. Key for useful swarm intelligence is the joint work on urban innovations as well as exchange and analysis of data”, Stadler said. Goals of the collaboration are techniques that reduce the space requirements of vehicles in urban spaces and improve the traffic flow. Within the scope of the project Audi plans to implement a connected infrastructure and piloted parking. According to Audi’s belief, self-parking vehicles can offer three benefits: Parking garages can be moved from the cities to less attractive areas of cities. At the same time, the space required to park for a car can be reduced by about two square metres (about 21 square feet) since with automated parking schemes in place, the vehicles can be parked closer together and require narrower lanes in the garages. Since the cars move autonomously, no paths for pedestrians, staircases and elevators are required any longer, which reduces the size of the parking garages by about 60 percent for the same number of cars, estimates Audi. 24 Electronic Engineering Times Europe December 2015 www.electronics-eetimes.com


EETE DEC 2015
To see the actual publication please follow the link above