IP Library › Granted Patent US 12,737,622
Granted Patent B2
US 12,737,622 · App. 18/177,689 · Granted Sep 15, 2026

ANN training trough processing power of parked vehicles

Inventors: Gil Golov (Backnang, DE); Robert Richard Noel Bielby (Placerville, CA)
Assignee: Micron Technology, Inc.
G06N3/08G06N3/045
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,737,622
App. No.
18/177,689
Granted
Sep 15, 2026
Kind
B2
Abstract

A system for ANN training through processing power of parked vehicles. The system can include a master computing device having a controller configured to control training of an ANN. The training can be performed at least partially in separate parts by computing devices of parked vehicles. The controller can be configured to separate computing tasks of training the ANN into separated tasks. Also, the controller can be configured to assign at least some of the separated tasks to selected computing devices of parked vehicles. The controller can also be configured to receive and assemble results of the separated tasks to train the ANN. The controller can also be configured to train the ANN according to the results. The master computing device can be configured to send the assigned tasks to the selected devices of the vehicles as well as receive, from the selected devices, the results of the assigned tasks.

Claims (38)

1 . An apparatus comprising:

at least one processing device; and

memory containing instructions configured to instruct the at least one processing device to:

control training for an artificial neural network (ANN);

maintain, in a queue, links to computing devices of a plurality of vehicles, wherein the computing devices perform tasks for training the ANN; and

remove a link in the queue to the at least one computing device based on receipt of a notification of a probability of a state change of the at least one computing device of the computing devices within a time period.

2 . The apparatus of claim 1 , wherein removing a link comprises reassigning a task from the at least one computing device to another computing device.

3 . The apparatus of claim 1 , wherein the instructions are further configured to instruct the processing device to receive a notification from the at least one computing device regarding a respective processing capability, and separate computing tasks of training the ANN into separated tasks.

4 . The apparatus of claim 3 , wherein the instructions are further configured to instruct the processing device to assign the separated tasks to computing devices of the vehicles.

5 . The apparatus of claim 1 , wherein the instructions are further configured to instruct the processing device to deselect a first computing device of a first vehicle in response to a notification from the first vehicle regarding resource availability.

6 . The apparatus of claim 1 , wherein links are added to the queue or removed from the queue based on information received from the vehicles regarding a state of an ECU of the respective vehicle.

7 . The apparatus of claim 1 , wherein links are added to the queue or removed from the queue based on information received from the vehicles regarding activity associated with respective transmissions of the vehicles.

8 . The apparatus of claim 1 , wherein a first notification from a first computing device includes data regarding an indication of a person entering a vehicle.

9 . The apparatus of claim 1 , wherein adding a link to the queue is subject to receiving a notification from a corresponding computing device indicating that the computing device is authorized for training the ANN.

10 . An apparatus comprising:

at least one processing device; and

memory containing instructions configured to instruct the at least one processing device to:

control training for an artificial neural network (ANN);

maintain, in a queue, links to computing devices of a plurality of vehicles, wherein the computing devices perform tasks for training the ANN;

receive a notification from a first computing device indicating that the first computing device is not available for training the ANN and indicating a probability of a state change of the first computing device within a time period; and

in response to receiving the notification, remove a link in the queue to the first computing device.

11 . The apparatus of claim 10 , wherein the at least one processing device is further instructed to deselect the first computing device based on the probability of the state change of the first computing device within the time period.

12 . The apparatus of claim 11 , wherein the at least one processing device is further instructed to remove the link in the queue to the first computing device after the first computing device is deselected.

13 . The apparatus of claim 10 , wherein the at least one processing device is further instructed to reassign at least one task associated with training the ANN assigned to the first computing device to a second computing device of the computing devices.

14 . The apparatus of claim 10 , wherein the at least one processing device is further instructed to determine if the first computing device is authorized to train the ANN.

15 . The apparatus of claim 10 , wherein the at least one processing device is further instructed to terminate at least one task intended for the first computing device in response to the notification.

16 . The apparatus of claim 10 , wherein the at least one processing device is further instructed to add a second link to the queue for a second computing device of the computing devices based on a processing capability of the second computing device.

17 . The apparatus of claim 10 , wherein the at least one processing device is further instructed to separate the tasks for training the ANN to be performed by each computing device of the computing devices.

18 . The apparatus of claim 10 , wherein the at least one processing device is further instructed to send the tasks to at least one other computing device of the computing devices after removing the link to the first computing device.

19 . An apparatus comprising:

at least one processing device; and

memory containing instructions configured to instruct the at least one processing device to:

control training for an artificial neural network (ANN);

maintain, in a queue, links to computing devices of a plurality of vehicles, wherein the computing devices perform tasks for training the ANN, the maintaining including removing a first link to a first computing device based on receipt of a notification indicating a probability of a state change for the first computing device within a time period;

separate computing tasks of training the ANN into separated tasks; and

assign the separated tasks to the computing devices of the vehicles.

20 . The apparatus of claim 19 , wherein the at least one processing device is further instructed to add a second link to a second computing device based on a different notification indicating a state change for the second computing device.

21 . The apparatus of claim 20 , wherein the at least one processing device is further configured to receive a result of processing at least one task of the tasks assigned to the second computing device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 2, 2023
From: GOLOV, GIL; BIELBY, ROBERT RICHARD NOEL
To: MICRON TECHNOLOGY, INC.
Reel/Frame 062863/0414 →
Continuity (2)
Continuation 16850946 · Apr 16, 2020
Related Publication 20230206071A1 · Jun 29, 2023
References Cited (20)
US 10106153B1 · Xiao · 2018 [cited by examiner]
US 10395144B2 · Zeng · 2019 [cited by examiner]
US 10991242B2 · Taylor · 2021 [cited by examiner]
US 11604989B2 · Golov · 2023 [cited by examiner]
US 11675618B2 · Park · 2023 [cited by examiner]
US 20100165997A1 · Matsumoto · 2010 [cited by examiner]
US 20160050718A1 · Follman · 2016 [cited by applicant]
US 20180341525A1 · Gupta et al. · 2018 [cited by applicant]
US 20190041852A1 · Schubert et al. · 2019 [cited by applicant]
US 20190050718A1 · Tickoo · 2019 [cited by examiner]
US 20190095796A1 · Chen et al. · 2019 [cited by applicant]
US 20190205744A1 · Mondello et al. · 2019 [cited by applicant]
US 20190295013A1 · Lhota et al. · 2019 [cited by applicant]
US 20190392307A1 · Liao et al. · 2019 [cited by applicant]
US 20200027019A1 · Yang et al. · 2020 [cited by applicant]
US 20210326692A1 · Golov et al. · 2021 [cited by applicant]
Extended European Search Report, EP21788563.1, mailed on Apr. 9, 2024. [cited by applicant]
Huang, Jin, et al., “Using NARX Neural Network based Load Prediction to Improve Scheduling Decision in Grid Environments.” Third International Conference on natural Computation, IEEE, Aug. 1, 2007. [cited by applicant]
International Search Report and Written Opinion, PCT/US2021/026972, mailed on Jul. 23, 2021. [cited by applicant]
Title: Ann Training through Processing Power of Parked Vehicles, U.S. Appl. No. 16/850,946, filed Apr. 16, 2020, Confirmation: 5822, Status Date: Feb. 22, 2023, Inventors: Gil Golov, et al., Status: Patented Case. [cited by applicant]