Orama.AOI optimized Akida for tire and semiconductor packaging defect detection. Deployed to production.
Higher accuracy. 4 to 6 watts. 3 to 5x lower system cost than GPU alternatives. Updates ship over the air.
Link Below.
bit.ly/3TRLZJr
BrainChip
@BrainChip_inc
Intelligence at the Edge. Always-On. Private. Physical.
- Our CEO Sean Hehir talked edge AI, BVLOS, and drone swarming with Drones World Magazine this month. Full interview below 👇 bit.ly/4xtUzN0
- Under 1 watt ⚡ That's the whole power budget behind the spec @EFYmagonline called out this month when they named the AKD1500 a Truly Innovative Tech pick 🏆 No cloud round-trip, no burning through a battery just to get pattern recognition running on a microcontroller. 🔗
- Most wearables don't die from sensing too much. They die from calling the cloud too often. AKD1500 runs fall detection on-device instead. Link below. bit.ly/4x1nw2p
- Nobody asks a wearable chip for more TOPS. They ask for more battery life. AKD1500 M.2 Card: 250mW typical, 800 Effective GOPS (INT4), M.2 2230. Built for always-on sensing and at-sensor inference, not benchmark bragging rights. Specs below. bit.ly/4x1nw2p
