METHOD AND DEVICE FOR PRE-PROCESSING DATA IN A NEURAL NETWORK

(19)

(11)

EP 3 757 896 A8

(12)	CORRECTED EUROPEAN PATENT APPLICATION
	Note: Bibliography reflects the latest situation

(15)	Correction information:
	Corrected version no 1 (W1 A1)

(48)	Corrigendum issued on:
	14.09.2022 Bulletin 2022/37

(43)	Date of publication:
	30.12.2020 Bulletin 2020/53

(21)	Application number: 19217269.0

(22)	Date of filing: 27.06.2019

(51)

International Patent Classification (IPC):

G06N 3/04^(2006.01)

G06F 12/0802^(2016.01)

(52)	Cooperative Patent Classification (CPC):
	G06F 12/0802; G06F 2212/1044; G06F 2212/454; G06N 3/0454; G06N 3/063; G06F 12/0888; G06F 2212/1016; G06F 12/0811; G06F 12/0804; G06F 2212/604; G06F 13/1668; G06N 3/08; G06N 20/10

(84)	Designated Contracting States:
	AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

(30)

Priority:

28.08.2018 CN 201810987293
28.08.2018 CN 201810987343

(62)	Application number of the earlier application in accordance with Art. 76 EPC:
	19812653.4 / 3640810

(71)	Applicant: Cambricon Technologies Corporation Limited
	Beijing 100190 (CN)

(72)	Inventors:
	LIU, Shaoli Beijing, 100190 (CN) MENG, Xiaofu Beijing, 100190 (CN)

(74)	Representative: Huang, Liwei
	Cäcilienstraße 12 40597 Düsseldorf 40597 Düsseldorf (DE)


	Remarks:
	This application was filed on 18-12-2019 as a divisional application to the application mentioned under INID code 62.

(54)	METHOD AND DEVICE FOR PRE-PROCESSING DATA IN A NEURAL NETWORK

(57) The present disclosure provides a pre-processing method and device of data, a computer device, and a storage medium. By storing the target output data corresponding to the target operation into the primary memory close to the processor and reducing the times of reading the target output data, the occupation time of the I/O read operation during the operation process can be reduced, so that the speed and efficiency of the processor can be improved.