2025 BrainChip Discussion, page-4282

BrainChip is featuring our SOTA accuracy eye-tracking TENNs model executing on our Akida event-based neuromorphic IP, for integration into wearable devices with single digit mW power dissipation .  

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, AkidaTM, uses neuromorphic principles to mimic the human brain. Analyzing only essential sensor inputs at the point of acquisition, Akida processes data with unparalleled efficiency, precision and economy of energy. Akida Neural Processor IP, when integrated into SoCs on any digital process technology, has shown substantial benefits on today’s workloads and networks. It offers a platform for developers to create, tune and run their models using standard AI workflows like Tensorflow/Keras.

BrainChip’s Temporal Event-based Neural Networks (TENNs) models expand upon state space models (SSMs) by adding a time-sensitive, event-driven processing paradigm that makes them even more efficient and better suited for real-time streaming Edge applications. In enabling effective compute with efficient models and hardware execution, real-time streaming Edge AI can be universally deployable across real-world uses in space, aeronautical, autonomous vehicles, robotics, mobile, consumer and wearable products. BrainChip is proving that ultra-low power, on-chip AI, close to the sensor, is the future for its customers’ products, as well as the planet. Explore the benefits at www.brainchip.com.