MENU

Low-power sensAI facilitates AI in edge devices

Low-power sensAI facilitates AI in edge devices

By eeNews Europe



Lattice sensAI is intended to accelerate the integration of machine learning into IoT applications. There is a variety of solutions on offer that prioritise ultra-low power consumption (under 1 mW–1 W), small package size (5.5 mm2 –100 mm2), interface flexibility (MIPI CSI-2, LVDS, GigE, etc.), and high-volume pricing (~$1-$10 USD)

The sensAI stack includes:

 Modular Hardware Platforms – ECP5TM device-based Video Interface Platform (VIP), including the Embedded Vision Development Kit, and iCE40 UltraPlus device-based Mobile Development Platform (MDP).

 IP Cores – Convolutional Neural Network (CNN) accelerator and Binarized Neural Network (BNN) accelerator.

 Software Tools – Neural network compiler tool for Caffe/TensorFlow to FPGA, Lattice Radiant design software, Lattice Diamond design software.

 Reference Designs – Face detection, key phrase detection, object counting, face tracking, and speed sign detection.

 Design Services – Ecosystem of design service partners delivers custom solutions for broad market applications, including smart home, smart city, and smart factory.

More information

www.latticesemi.com/sensAI

Related news

New Qualcomm IoT processors show no sign of dedicated neural network hardware

Infineon: Deep learning neural networks demand sophisticated power

IAR Embedded Workbench now supports Arm’s CMSIS-NN neural network library

Ceva goes non-DSP with neural processor

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News

Share:

10s