公开(公告)号：US20190147322A1

公开(公告)日：2019-05-16

申请号：US16044163

申请日：2018-07-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Do-yun KIM ,  Han-young YIM ,  Byeoung-su KIM ,  Nak-woo SUNG ,  Jong-han LIM ,  Sang-hyuck HA

IPC: G06N3/04 ,  G06N3/08 ,  G06F17/18

Abstract: An artificial neural network (ANN) quantization method for generating an output ANN by quantizing an input ANN includes: obtaining second parameters by quantizing first parameters of the input ANN; obtaining a sample distribution from an intermediate ANN in which the obtained second parameters have been applied to the input ANN; and obtaining a fractional length for the sample distribution by quantizing the obtained sample distribution.

公开(公告)号：US20190095777A1

公开(公告)日：2019-03-28

申请号：US16008275

申请日：2018-06-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Do-yun KIM ,  Han-young YIM ,  In-yup KANG ,  Byeoung-su KIM ,  Nak-woo SUNG ,  Jong-Han LIM ,  Sang-hyuck HA

IPC: G06N3/04 ,  G06N3/08

Abstract: A method of quantizing an artificial neural network includes dividing an input distribution of the artificial neural network into a plurality of segments, generating an approximated density function by approximating each of the plurality of segments, calculating at least one quantization error corresponding to at least one step size for quantizing the artificial neural network, based on the approximated density function, and determining a final step size for quantizing the artificial neural network based on the at least one quantization error.