Lattice Semiconductor announced the availability of performance enhancements and improved application reference designs for its sensAI solutions stack. sensAI develops AI and ML experiences for next-generation smart devices with milliwatt-level power consumption.
The enhancements include support for more compact/efficient neural network models and deeper quantization support to accommodate larger models for processing higher resolution and/or faster frames-per-second images in vision applications.
The latest enhancements include:
- sensAI on the iCE40 UltraPlus FPGA now supports 8-bit quantization.
- sensAI on the ECP5 FPGA now supports the MobileNet and ResNet neural network models.
- Key phrase detection for AI/ML-enabled human machine interface applications using microphones.
- Human face recognition, which in addition to detecting a human face can now identify specific registered users.
- Wake-on approach for printers and laptops
- Defect detection and operator compliance in industrial smart cameras
For more information, visit www.latticesemi.com/sensAI.