Fast and Light-weight Binarized Neural Network Implemented in an FPGA using LUT-based Signal Processing and its Time-domain Extension for Multi-bit Processing.
Ryuji FuchikamiFumio IssikiPublished in: ICCE-Berlin (2019)
Keyphrases
- lightweight
- signal processing
- neural network
- hardware implementation
- reconfigurable hardware
- video processing
- pattern recognition
- signal acquisition
- fpga device
- real time image processing
- image processing
- real time
- frequency domain
- fourier transform
- digital signal processing
- computer vision
- artificial neural networks
- low cost
- field programmable gate array
- parallel architecture
- brain computer interface
- processing elements
- bounding box
- neural network model
- data acquisition
- document images
- wireless sensor networks