Hehir: “Our growing IP portfolio is the result of more than 15 years of AI architecture research and development”

Webp seanf
Sean Hehir, CEO of BrainChip | Linked in | Sean Hehir

BrainChip Holdings Ltd.  was recently issued a patent by IP Australia to leverage its 2nd generation Akida™ IP and expand its technology portfolio,  “extending its competitive advantage in performing efficient transposed and dilated convolutions in a neural network.”

“Our growing IP portfolio is the result of more than 15 years of AI architecture research and development,” Sean Hehir, CEO of BrainChip said. “As we continue to innovate and improve our technology, we enable our partners to create unprecedented intelligent Edge devices and applications. This patent from IP Australia further cements our leadership as the world’s first commercial producer of neuromorphic IP.”

The patent identified as AU 2022203607 and “Event-Based Extraction of Features in a Convolutional Spiking Neural Network, is intended to reduce the computer and power-related needs of event-based transposed and dilated convolution techniques, “compared to non-event-based convolutions by requiring a smaller number of even-based neuron circuits,” a recent Business Wire press release states.

The technology is currently in the advanced stages of development for the implementation of the 2nd generation Akida IP.

The Australian company, with offices in California has now established 12 patents in the U.S, 4 in Australia, one in Europe and one in China. The company has thirty patent applications in the US, Europe, Canada, Australia, Japan, Korea, India, Brazil, Russia, Mexico, and Israel.

“BrainChip is the worldwide leader in edge AI on-chip processing and learning. The company’s first-to-market, fully digital, event-based AI processor, Akida, uses neuromorphic principles to mimic the human brain, analyzing only essential sensor inputs at the point of acquisition, processing data with unparalleled efficiency, precision, and economy of energy,” the press release states. “Akida uniquely enables edge learning local to the chip, independent of the cloud, dramatically reducing latency while improving privacy and data security. “

Related