US 11,853,894 B2
Meta-learning for multi-task learning for neural networks
Andrew Rabinovich, San Francisco, CA (US); Vijay Badrinarayanan, Mountain View, CA (US); Srivignesh Rajendran, San Francisco, CA (US); and Chen-Yu Lee, Sunnyvale, CA (US)
Assigned to Magic Leap, Inc., Plantation, FL (US)
Filed by Magic Leap, Inc., Plantation, FL (US)
Filed on Jun. 10, 2021, as Appl. No. 17/344,758.
Application 17/344,758 is a continuation of application No. 16/185,582, filed on Nov. 9, 2018, granted, now 11,048,978.
Claims priority of provisional application 62/586,154, filed on Nov. 14, 2017.
Prior Publication US 2021/0406609 A1, Dec. 30, 2021
Int. Cl. G06N 3/084 (2023.01); G06F 18/21 (2023.01); G06N 3/04 (2023.01); G06N 3/044 (2023.01); G06N 3/047 (2023.01)
CPC G06N 3/084 (2013.01) [G06F 18/217 (2023.01); G06N 3/04 (2013.01); G06N 3/044 (2023.01); G06N 3/047 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A system for training a neural network to learn a set of tasks, the system comprising:
non-transitory memory configured to
store: executable instructions;
and
a child network for learning a plurality of tasks, wherein the child network is associated with a loss function for the plurality of tasks and a task weight is assigned to each task of the plurality of tasks;
a hardware processor in communication with the non-transitory memory, the hardware processor programed by the executable instructions to:
determine a first child network loss associated with the loss function of the child network;
determine an updated task weight for each task of the plurality of tasks based on the first child network loss;
determine an updated child network based on the updated task weight for each task of the plurality of tasks;
determine a second child network loss associated with the loss function of the updated child network; and
determine a second updated task weight for each task of the plurality of tasks based at least on the second child network loss.