US 12,334,956 B2
Data processing system and data processing method for deep neural network model
Yu-Chih Huang, Hsinchu (TW); and Li-Yang Tseng, Hsinchu (TW)
Assigned to Industrial Technology Research Institute, Hsinchu (TW)
Filed by Industrial Technology Research Institute, Hsinchu (TW)
Filed on Nov. 29, 2023, as Appl. No. 18/522,242.
Claims priority of provisional application 63/433,020, filed on Dec. 16, 2022.
Claims priority of application No. 112138426 (TW), filed on Oct. 6, 2023.
Prior Publication US 2024/0204804 A1, Jun. 20, 2024
Int. Cl. H03M 13/27 (2006.01); H03M 13/00 (2006.01); H04L 1/00 (2006.01)
CPC H03M 13/27 (2013.01) [H03M 13/6577 (2013.01); H04L 1/0041 (2013.01); H04L 1/0045 (2013.01); H04L 1/0071 (2013.01)] 14 Claims
OG exemplary drawing
 
8. A data processing method for a deep neural network model, comprising:
reading a plurality of weights from a transmission data;
quantizing each of the weights into a plurality of bits, wherein the bits sequentially comprise a first-type bit, a plurality of second-type bits, a third-type bit, and a plurality of fourth-type bits;
interleaving the first-type bit in each of the weights into a first bit set;
sequentially interleaving each of the second-type bits in each of the weights into a plurality of second bit sets, and reading a second compression rate of each of the second bit sets in response to the second bit sets being compressible;
interleaving the third-type bit in each of the weights into a third bit set, and reading a third compression rate of the third bit set in response to the third bit set being compressible;
compressing each of the second bit sets with the second compression rate, and compressing the third bit set with the third compression rate;
sequentially coding the first bit set, each of the compressed second bit sets, and the compressed third bit set to generate a first encoded data corresponding to the transmission data; and
transmitting the first encoded data to an external device.