BrainChip strenthgens IP portfolio with event-based pattern detection patent
Cette publication existe aussi en Français
BrainChip Holdings Ltd, the first commercial producer of ultra-low power, fully digital, event-based, neuromorphic AI IP, was issued its latest U.S. patent, further strengthening its IP portfolio related to sustainable and efficient AI technologies.
Patent US 11,853,862, “Method, Digital Electronic Circuit and System for Unsupervised Detection of Repeating Patterns in a Series of Events,” facilitates learning in a digital hardware implementation of a spiking network. A key aspect of this unique approach is its effectiveness in performing accurate unsupervised detection or learning of repeating patterns, even when these patterns are embedded in high levels of noise, while being extremely efficient in reducing computing time, energy consumption and silicon footprint.
BrainChip’s Akida™ IP and MetaTF™ tools seamlessly transform contemporary neural networks into event-based or spiking networks. This patented technology uniquely synergizes with the converted spiking networks, enabling the streamlined deployment of edge learning algorithms and unlocking use cases that conventional AI tools or solutions cannot attain.
Akida™ IP achieves very high performance with an extremely low-power budget and a negligible thermal footprint. Its performance per microwatt can be orders of magnitude better than the current options on the market. Designed for sustainable AI, Akida performs complex functions at the device level, delivering a real-time, instant response.
MetaTF is used for the creation, training, and testing of neural networks. MetaTF supports the development of systems for Edge AI on Brainchip’s Akida event domain neural processor.
“While we push the bounds with our innovative neuromorphic technology, preserving its integrity is paramount,” said Sean Hehir, CEO of BrainChip. “With 13 patents issued in the U.S. alone, we stand as leaders in developing and implementing next generation AI technologies for intelligent Edge devices and on-chip processing.”
BrainChip’s portfolio now comprises 19 issued patents (13x US, 4x AU, 1x EP, 1x CN). In addition, there are nearly 30 pending patent applications across the US, Europe, Australia, Canada, Japan, Korea, India, Brazil, Russia, Mexico, and Israel.
Related articles
China boosts AI chip self-sufficiency but high-end elusive
PCIe accelerator card cuts power consumption in AI servers
Partnership brings energy saving AI technology to home appliances
Edge AI processor tackles demands of Generative AI, video and LLMs
VeriSilicon, Google promote efficient, safe AI with Open Se Cura project
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
