US 12,293,276 B2
Neural architecture search with factorized hierarchical search space
Mingxing Tan, Newark, CA (US); Quoc Le, Sunnyvale, CA (US); Bo Chen, Pasadena, CA (US); Vijay Vasudevan, Los Altos Hills, CA (US); and Ruoming Pang, New York, NY (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Feb. 1, 2024, as Appl. No. 18/430,483.
Application 18/430,483 is a continuation of application No. 18/154,321, filed on Jan. 13, 2023, granted, now 11,928,574.
Application 18/154,321 is a continuation of application No. 17/495,398, filed on Oct. 6, 2021, abandoned.
Application 17/495,398 is a continuation of application No. 16/258,927, filed on Jan. 28, 2019, granted, now 11,531,861, issued on Dec. 20, 2022.
Claims priority of provisional application 62/756,254, filed on Nov. 6, 2018.
Prior Publication US 2024/0273336 A1, Aug. 15, 2024
Int. Cl. G06N 3/04 (2023.01); G06F 17/15 (2006.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/084 (2023.01); G06N 20/10 (2019.01)
CPC G06N 3/04 (2013.01) [G06F 17/15 (2013.01); G06N 3/044 (2023.01); G06N 3/084 (2013.01); G06N 20/10 (2019.01); G06N 3/045 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, the method comprising:
defining, by one more computing devices, an initial network structure for an artificial neural network, the initial network structure comprising a plurality of blocks;
associating, by the one or more computing devices, a plurality of sub-search spaces respectively with the plurality of blocks, wherein the sub-search space for each block has one or more searchable parameters associated therewith, wherein the one or more searchable parameters included in the sub-search space associated with at least one of the plurality of blocks comprise a number of layers included in the block; and
for each of one or more iterations:
modifying, by one or more computing devices, at least one of the searchable parameters in the sub-search space associated with at least one of the plurality of blocks to generate a new network structure for the artificial neural network.