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 |
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.
|