US 11,797,848 B2
Data compression apparatus, data compression method, and learning apparatus
Hidenori Takeshima, Kawasaki (JP)
Assigned to Canon Medical Systems Corporation, Otawara (JP)
Filed by Canon Medical Systems Corporation, Otawara (JP)
Filed on Apr. 27, 2022, as Appl. No. 17/660,897.
Application 17/660,897 is a division of application No. 16/934,083, filed on Jul. 21, 2020, granted, now 11,367,000.
Claims priority of application No. 2019-148761 (JP), filed on Aug. 14, 2019.
Prior Publication US 2022/0253703 A1, Aug. 11, 2022
Int. Cl. G06K 9/00 (2022.01); G06N 3/08 (2023.01); G06T 11/00 (2006.01); G06T 7/00 (2017.01); G16H 30/40 (2018.01); G06N 3/04 (2023.01); G16H 50/20 (2018.01)
CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01); G06T 7/0014 (2013.01); G06T 11/003 (2013.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G06T 2207/10081 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 1 Claim
OG exemplary drawing
 
1. A learning apparatus comprising processing circuitry configured to:
acquire reconstructed data generated by performing reconstruction processing on data;
acquire decompressed reconstructed data generated by performing the reconstruction processing on decompressed data obtained by decompressing compressed data that is generated by performing compression processing on the data; and
generate a trained model, to which data is input and which outputs compressed data, by training a coefficient of a neural network using a loss function, the loss function relating to (1) an error between the reconstructed data and the decompressed reconstructed data and (2) an error between the data and the decompressed data.