BrainChip examines a new approach to optimizing time series data

[ad_1]

LAGUNA HILLS, Calif., June 11, 2023–(BUSINESS WIRE)–A new white paper from BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s leading commercial manufacturer of ultra-low power devices, All-digital, event-driven, neuromorphic AI IP unveils temporal event-based neural networks (TENN), an innovative way to bring greater accuracy and efficiency to complex models on compact edge devices. TENNs are extremely effective in accelerating 3D and 1D time series applications, including video, vision, audio, and vital signs in healthcare, just to name a few.

The paper, “Temporal Event-Based Neural Networks: A Novel Approach to Temporal Computing,” shows how TENNs enable intelligent and energy-efficient edge solutions and details how BrainChips’ Akida 2nd Generation IP platform supports this innovation. TENNs provide radical and innovative ways to reduce complexity, size and compute requirements, while still delivering the precision expected for the desired intelligent and responsive experience at the edge.

“Although CNNs have long been the backbone of image classification in AI and ML, they are not as efficient at handling data and spatiotemporal applications such as detecting video objects from video streams and time-series data, thus limiting their use of cost-effective, thermally constrained edge devices,” said Anil Mankar, co-founder and CDO of BrainChip. “TENN is a new approach that leverages temporal correlations much more efficiently, revolutionizing AI at the edge.”

To learn more about how TENNs power continuous-over-time streaming raw data processing and time-series analysis used in forecasting and predictive maintenance, interested parties can download the white paper at https:// brainchip.com/wp-content/uploads/2023 /06/TENNs_Whitepaper_Final.pdf

About BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY)

BrainChip is the world leader in edge AI on-chip computing and learning. AkidaTM, the first all-digital event-based AI processor on the market, uses neuromorphic principles to mimic the human brain, analyzing only essential sensor inputs at the point of acquisition, processing the data with unmatched efficiency, accuracy and economy of energy . Akida uniquely enables edge learning local to the chip, independent of the cloud, dramatically reducing latency and improving data privacy and security. The Akida Neural processor IP, which can be integrated into SoCs on any process technology, has shown substantial benefits on today’s workloads and networks and offers developers a platform to build, tune and run their models using standard AI workflows like Tensorflow/Keras. By enabling the universal deployment of effective edge computing in real-world applications such as connected cars, consumer electronics, and industrial IoT, BrainChip is proving that AI on a chip, near the sensor, is the future, even for consumer products. its customers like the planet. Explore the benefits of Essential AI at www.brainchip.com.

The story continues

Follow BrainChip on Twitter: https://www.twitter.com/BrainChip_inc Follow BrainChip on LinkedIn: https://www.linkedin.com/company/7792006

View the source version at businesswire.com: https://www.businesswire.com/news/home/20230611628809/en/

Contacts

Media Contact: Mark Smith JPR Communications 818-398-1424

Investor Relations: Tony DaweDirector, Global Investor [email protected]

[ad_2]