Parallelism-flexible Convolution Core for Sparse Convolutional Neural Networks on FPGA.
Salita SombatsiriSeiya ShibataYuki KobayashiHiroaki InoueTakashi TakenakaTakeo HosomiJaehoon YuYoshinori TakeuchiPublished in: IPSJ Trans. Syst. LSI Des. Methodol. (2019)
Keyphrases
- convolutional neural networks
- convolutional network
- low cost
- high speed
- image processing
- signal processing
- sparse representation
- hardware implementation
- software implementation
- real time
- data acquisition
- parallel processing
- field programmable gate array
- hardware design
- sparse coding
- shared memory
- computational power
- discrete fourier transform
- sparse matrix
- high dimensional