BrainChip,
a leading provider of ultra-low power, high performance edge AI
technology, has been awarded a new patent for dynamic neural function
libraries, a key component of its AI processing chip Akida.
United
States Patent number 10,410,117 addresses a dynamic neural network
within an AI device. During a learning process, values are generated and
stored in the synaptic registers of the AI device to generate a
training model. Training models are themselves stored in the dynamic
neural function library of the AI device, and the function library can
then be used to train another device.
The
innovation was credited to Peter Van der Made, BrainChip founder and
CTO, who has been at the forefront of computer innovation for 40 years.
Van der Made is the inventor of a computer immune system at
cybersecurity developer vCIS Technology, where he served as CTO and
later Chief Scientist when it was acquired by Internet Security Systems
and subsequently IBM. Previously, he designed a high resolution,
high-speed color Graphics Accelerator Chip for IBM PC graphics. Van der
Made is the author of the book Higher Intelligence, which explains the architecture of the brain from a computer science perspective.
"This
patent addresses efficiency that contributes to how Akida technology
excels in speed, accuracy, and ultra-low power consumption," said Van
der Made. "Synapses store values, these thousands of synapses connect to
thousands of neurons, and that neural output can be used by another set
of neurons - which is closer to the way the human brain processes
information."
BrainChip's
intellectual portfolio consists of 11 patents issued or in process,
including a foundational patent in the area of Spiking Neural Networks
(SNN) that has been cited by leading companies such as IBM, Qualcomm,
Samsung, and Hewlett Packard.
With
the proliferation of intelligence into edge devices, there is a new and
growing need for fast, small, and power-efficient neural network
processors. By performing neural processing and memory accesses on the
edge, Akida vastly reduces the computing resources required of the host
CPU. This unprecedented efficiency not only delivers faster results, it
consumes only a tiny fraction of the power resources of traditional AI
processing, reducing the high environmental and economic costs of
running hyperscale data centers. Akida is available as a licensable IP
technology that can be integrated into ASIC devices and will be
available as an integrated SoC, both suitable for applications such as
surveillance, advanced driver assistance systems (ADAS), autonomous
vehicles (AV), vision guided robotics, drones, augmented and virtual
reality (AR/VR), acoustic analysis, and Industrial Internet-of-Things
(IoT).