18544169. PRACTICAL ACTIVATION RANGE RESTRICTION FOR NEURAL NETWORK QUANTIZATION (QUALCOMM Incorporated)
PRACTICAL ACTIVATION RANGE RESTRICTION FOR NEURAL NETWORK QUANTIZATION
Organization Name
Inventor(s)
Kanghwan Jang of San Diego CA US
Christopher Lott of San Diego CA US
Liang Zhang of San Diego CA US
PRACTICAL ACTIVATION RANGE RESTRICTION FOR NEURAL NETWORK QUANTIZATION
This abstract first appeared for US patent application 18544169 titled 'PRACTICAL ACTIVATION RANGE RESTRICTION FOR NEURAL NETWORK QUANTIZATION
Original Abstract Submitted
A processor-implemented method determines a practical domain for a following function in a following layer of an artificial neural network. The artificial neural network includes a leading function in a leading layer and the following function in the following layer, which is a subsequent consecutive layer of the artificial neural network. The method also sets a first quantization range of an output activation of the leading function based on the practical domain.
(Ad) Transform your business with AI in minutes, not months
✓
Custom AI strategy tailored to your specific industry needs
✓
Step-by-step implementation with measurable ROI
✓
5-minute setup that requires zero technical skills
Trusted by 1,000+ companies worldwide
