An Efficient Parallel Architecture for Convolutional Neural Networks Accelerator on FPGAs.
Hongmin HuangXueming LiYadong QinXianghong HuXiaoming XiongPublished in: HP3C (2022)
Keyphrases
- parallel architecture
- convolutional neural networks
- hardware implementation
- field programmable gate array
- parallel implementation
- parallel processing
- systolic array
- convolutional network
- high level synthesis
- shared memory
- distributed memory
- synthetic aperture sonar
- efficient implementation
- signal processing
- processing elements
- parallel algorithm
- massively parallel
- higher order
- dynamic programming
- multiresolution
- computational complexity
- optimal solution