Abstract | ||
---|---|---|
Deep neural network (NN) has been widely accepted for enabling various AI applications, however, the limitation of computational and memory resources is a major problem on mobile devices. Quantized NN with a reduced bit precision is an effective solution, which relaxes the resource requirements, but the accuracy degradation due to its numerical approximation is another problem. We propose a novel quantized NN model employing the "dithering" technique to improve the accuracy with the minimal additional hardware requirement at the view point of the hardware-algorithm co-designing. Dithering distributes the quantization error occurring at each pixel (neuron) spatially so that the total information loss of the plane would be minimized. The experiment we conducted using the software-based accuracy evaluation and FPGA-based hardware resource estimation proved the effectiveness and efficiency of the concept of an NN model with dithering. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1587/transinf.2019PAP0009 | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS |
Keywords | Field | DocType |
neural network, dithering, error diffusion, FPGA, hardware-oriented neural network algorithm | Computer vision,Co-design,Quantized neural networks,Computer science,Hardware algorithm,Artificial intelligence,Dither | Journal |
Volume | Issue | ISSN |
E102D | 12 | 1745-1361 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kota Ando | 1 | 24 | 6.81 |
Kodai Ueyoshi | 2 | 22 | 3.84 |
Yuka Oba | 3 | 3 | 2.82 |
Kazutoshi Hirose | 4 | 5 | 2.94 |
Ryota Uematsu | 5 | 1 | 1.79 |
Takumi Kudo | 6 | 0 | 0.34 |
M. Ikebe | 7 | 47 | 13.63 |
Tetsuya Asai | 8 | 121 | 26.53 |
Shinya Takamaeda-Yamazaki | 9 | 65 | 16.83 |
Masato Motomura | 10 | 91 | 27.81 |