A New Era in Edge Computing with 1000X More Energy Efficient Neural Networks
We Support a Diverse Set of End Markets in energy-starved applications for both consumer and industry. The company’s patented products increase an application’s functionality while remaining within its fixed battery capacity. We do this by processing data at the source thereby limiting power-hungry RF transmissions resulting in longer system life and significantly more features, all at lower costs.
Eta Compute’s Neural Sensor Platform brings Artificial Intelligence to edge devices and transforms sensor data into actionable information for voice, activity, gesture, sound, image, temperature, pressure and bio-metrics, among others. The platform delivers the trifecta in edge computing: lower response time, increased security, and higher accuracy.
Major Applications Leveraging Eta Compute’s Technology
What is Continuous Voltage & Frequency Scaling?
Cifar10 Image Recognition System consumes <1mJ per inference
Always on command recognition consumes 300uA
Semiconductor Digest March Edition – exerpt
Deep Learning at the Extreme Edge: A Manifesto
By Gopal Raghavan, Ph.D., Co-founder, Chief Technologist and Semir Haddad, Senior Director Product Marketing.
Upcoming Webinar with Semir Haddad on April 21 at 10:00 AM
“Artificial Intelligence in Micro-watts: How to make TinyML a reality” will be live on Semi Wiki.
Endpoint AI in Microwatts, Eta Compute has production of its first product
The ECM3532 promises to enable AI and ML computation in IoT applications for a power budget of just microwatts.
ETA compute, an example of successful startup, makes Edge AI assumptions a reality
ECM 3532, is a system on a chip, built around an Arm Cortex-M3 processor core and an NXP CoolFlux DSP core.