Neural network design method for memory calculation and judging whether someone is in room or not
A memory computing and neural network technology, which is applied in the field of neural network design for memory computing and whether there are people in the room, can solve the problems of reducing the amount of parameters and computing, short computing time, and keeping the accuracy rate unchanged. The effect of short calculation time and reduced number of parameters
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0027] Below in conjunction with accompanying drawing, the present invention is described in further detail:
[0028] A neural network design method for memory computing and whether there are people in the room has the following characteristics:
[0029] Design an ultra-lightweight neural network model, namely the UL-CNN model. The UL-CNN model is based on the rule that the chip based on the memory computing architecture is not sensitive to high levels, and the size of the memory is limited to 2K*2K, and the fixed-point processing is used to adjust the convolution operation and the fully connected matrix operation method, so that The UL-CNN model is applied on a chip based on memory computing architecture for inference, and finally detects whether there is a person in the room.
[0030] In order to comply with the computing rules of chips based on memory computing architecture (the present invention uses Conv-Flash chips), the size of the CNN array is 2k*2k. It graphically a...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com