US 11,699,097 B2
Machine learning model with conditional execution of multiple processing tasks
Francesco Rossi, Sunnyvale, CA (US); Vignesh Jagadeesh, San Jose, CA (US); Vinay Sharma, Palo Alto, CA (US); Marco Zuliani, San Jose, CA (US); Xiaojin Shi, Cupertino, CA (US); and Benjamin Poulain, San Jose, CA (US)
Assigned to APPLE INC., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on May 19, 2020, as Appl. No. 16/878,254.
Claims priority of provisional application 62/850,618, filed on May 21, 2019.
Prior Publication US 2020/0372408 A1, Nov. 26, 2020
Int. Cl. G06N 20/00 (2019.01); G06F 9/38 (2018.01)
CPC G06N 20/00 (2019.01) [G06F 9/3885 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving input data at a trained machine learning model that includes a common part and task-specific parts;
receiving an execution instruction at the trained machine learning model that identifies one or more processing tasks to be performed;
processing the input data using the common part of the trained machine learning model to generate intermediate data; and
processing the intermediate data using one or more of the task-specific parts of the trained machine learning model that correspond to the one or more processing tasks to be performed that are identified by the execution instruction to generate one or more outputs, wherein processing the intermediate data using the one or more of the task-specific parts of the trained machine learning model based on the execution instruction includes loading only the one or more of the task-specific parts of the trained machine learning model that are identified by the execution instruction.