US 12,136,030 B2
System and method for adapting a neural network model on a hardware platform
Michael Driscoll, Mountain View, CA (US)
Assigned to Tesla, Inc., Austin, TX (US)
Filed by Tesla, Inc., Austin, TX (US)
Filed on Mar. 16, 2023, as Appl. No. 18/185,142.
Application 18/185,142 is a continuation of application No. 16/728,884, filed on Dec. 27, 2019, granted, now 11,610,117.
Claims priority of provisional application 62/791,220, filed on Jan. 11, 2019.
Claims priority of provisional application 62/785,363, filed on Dec. 27, 2018.
Prior Publication US 2023/0289583 A1, Sep. 14, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/063 (2023.01); G06F 17/16 (2006.01); G06F 18/20 (2023.01); G06F 18/21 (2023.01); G06N 3/08 (2023.01)
CPC G06N 3/063 (2013.01) [G06F 17/16 (2013.01); G06F 18/217 (2023.01); G06F 18/29 (2023.01); G06N 3/08 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method implemented by a system of one or more processors, the method comprising:
obtaining neural network model information comprising a plurality of decision points associated with a neural network, wherein one or more first decision points are associated with a layout of the neural network;
determining, based on the platform neural network model information, constraints associated with adapting the neural network model information to a hardware platform, wherein a first constraint is associated with a processing resource of the hardware platform, wherein a second constraint is associated with a performance metric, and wherein the constraints are enforced on a per-layer or per-tensor basis; and
generating a candidate configuration for the neural network via execution of a satisfiability solver based on the constraints, wherein the candidate configuration assigns values to the plurality of decision points; and
responsive to updated constraints corresponding to the candidate configuration as a negation, generating an updated candidate configuration, such that the neural network is configured to the hardware platform.