DYNAMICALLY MODIFYING A BOUNDARY OF A DEEP LEARNING NETWORK

• US 20160098646A1
• Filed: 10/06/2014
• Published: 04/07/2016
• Est. Priority Date: 10/06/2014
• Status: Active Grant

• Current Assignee: Seagate Technology LLC (Seagate Technology Holdings Plc)
• Original Assignee: Seagate Technology LLC (Seagate Technology Holdings Plc)
• Inventors: Gomez, Kevin Arthur, Dropps, Frank, Goss, Ryan James, Trantham, Jon, Khoueir, Antoine
• Granted Patent: US 10,679,140 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/141 Setup of application sessions admission control or resource allocation in data switching networks H04L47/70

Abstract

A connection between a user device and a network server is established. Via the connection, a deep learning network is formed for a processing task. A first portion of the deep learning network operates on the user device and a second portion of the deep learning network operates on the network server. Based on cooperation between the user device and the network server, a boundary between the first portion and the second portion of the deep learning network is dynamically modified based on a change in a performance indicator that could affect the processing task

Claims

1. A method comprising:

establishing a connection between a user device and a network server;

forming, via the connection, a deep learning network for a processing task, a first portion of the deep learning network operating on the user device and a second portion of the deep learning network operating on the network server; and

based on cooperation between the user device and the network server, dynamically modifying a boundary between the first portion and the second portion of the deep learning network based on a change of a performance indicator that could affect the processing task.

2. The method of claim 1, wherein the change in the performance indicator occurs before the processing task is run.

3. The method of claim 1, wherein the boundary is modified after the processing task is complete for the benefit of subsequent similar processing tasks.

4. The method of claim 1, wherein the boundary comprises an interface between neural layers of the deep learning network.

5. The method of claim 1, wherein the boundary comprises an interface between hierarchical levels of the deep learning network.

6. The method of claim 1, wherein dynamically modifying the boundary comprises signaling between the user device and the network server to modify a current session.

7. The method of claim 1, wherein dynamically modifying the boundary comprises selecting different ones of multiple application program interfaces available between the user device and the network server.

8. The method of claim 1, wherein the processing task is performed on behalf of a user of the user device.

9. The method of claim 1, wherein the user device comprises a mobile device.

10. A network server, comprising:

a network interface;

a processor coupled to the network interface, the processor configured to;

establish a connection with a user device;

form, via the connection, a deep learning network for a processing task on behalf of the user device, wherein a first portion of the deep learning network operates on the user device and a second portion of the deep learning network operates on the network server; and

in cooperation with the user device, dynamically modify a boundary between the first portion and the second portion of the deep learning network based on a change in a performance indicator that could affect the processing task.

11. The network server of claim 10, wherein the change in the performance indicator occurs before the processing task is run.

12. The network server of claim 10, wherein the boundary comprises an interface between hierarchical levels of the deep learning network.

13. The network server of claim 10, wherein the boundary is dynamically modified based on signaling between the user device and the network server.

14. The network server of claim 10, wherein the boundary is dynamically modified based on selection of one of multiple interfaces available between the user device and the network server.

15. A user device, comprising:

a sensor;

a processor coupled to the sensor, the processor configured to;

encode signals from the sensor;

send the encoded signals to a neural network for a processing task, wherein a first portion of the neural network operates on the user device and a second portion of the neural network operates on a network server in communication with the user device; and

in cooperation with the network server, dynamically modify a boundary between the first portion and the second portion of the neural network based on a change in a performance indicator that could affect the processing task.

16. The user device of claim 15, wherein the change in the performance indicator occurs before the processing task is run.

17. The user device of claim 15, wherein the boundary comprises an interface between hierarchical levels of a deep-belief network.

18. The user device of claim 15, wherein the boundary is dynamically modified based on signaling between the user device and the network server.

19. The user device of claim 15, wherein the boundary is dynamically modified based on selection of one of multiple interfaces available between the user device and the network server.

20. The user device of claim 15, wherein the user device comprises a mobile device.