ENHANCING THE RELIABILITY OF LEARNING MACHINES IN COMPUTER NETWORKS

• US 20140222727A1
• Filed: 07/09/2013
• Published: 08/07/2014
• Est. Priority Date: 02/05/2013
• Status: Abandoned Application

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Vasseur, Jean-Philippe, Mermoud, Grgory, Dasgupta, Sukrit
• Application Number:
  US13/937,664
• Publication Number:
  US 20140222727A1
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

In one embodiment, network data is processed using a Learning Machine (LM) algorithm in a network, and results of the processing of network data are determined. A reliability checking algorithm is selected to determine a reliability level of the results. The reliability checking algorithm may be a local reliability checking algorithm or an external reliability checking algorithm. The reliability level of the results is determined using the reliability checking algorithm. Then, the LM algorithm is adjusted based on the determined reliability level.

Claims

1. A method, comprising:

processing network data using a Learning Machine (LM) algorithm in a network;

determining results of the processing of network data;

selecting a reliability checking algorithm to determine a reliability level of the results, the reliability checking algorithm being a local reliability checking algorithm or an external reliability checking algorithm;

determining the reliability level of the results using the reliability checking algorithm; and

adjusting the LM algorithm based on the determined reliability level.

2. The method according to claim 1, further comprising:

receiving one or more feedback messages indicating an improper operation of the LM algorithm.

3. The method according to claim 1, wherein the adjusting of the LM algorithm is based further on the one or more feedback messages.

4. The method according to claim 1, further comprising:

performing a counter-measure to increase the reliability level.

5. The method according to claim 4, further comprising:

determining whether the reliability level is below a predetermined threshold, wherein the counter-measure is performed when the reliability level is below the predetermined threshold.

6. The method according to claim 4, wherein the performing of the counter-measure is triggered by one of:

a criticality of one or more feedback messages and a rate of receipt of one or more feedback messages.

7. The method according to claim 4, wherein the counter-measure includes one of:

resetting the LM algorithm and processing the network data using a new LM algorithm.

8. The method according to claim 2, wherein the one or more feedback messages are generated by a user.

9. The method according to claim 2, further comprising:

when a number of received feedback messages is greater than a predetermined first threshold, terminating the LM algorithm.

10. The method according to claim 9, further comprising:

when the number of received feedback messages is greater than a predetermined second threshold and less than the predetermined first threshold, processing the network data using a new LM algorithm.

11. The method according to claim 10, further comprising:

receiving a message indicating the predetermined first threshold and the predetermined second threshold.

12. An apparatus, comprising:

one or more network interfaces that communicate with a network;

a processor coupled to the one or more network interfaces and configured to execute a process; and

a memory configured to store program instructions which contain the process executable by the processor, the process comprising;

processing network data using a Learning Machine (LM) algorithm in the network;

determining results of the processing of network data;

selecting a reliability checking algorithm to determine a reliability level of the results, the reliability checking algorithm being a local reliability checking algorithm or an external reliability checking algorithm;

determining the reliability level of the results using the reliability checking algorithm; and

is adjusting the LM algorithm based on the determined reliability level.

13. The apparatus according to claim 12, wherein the process further comprises:

receiving one or more feedback messages indicating an improper operation of the LM algorithm.

14. The apparatus according to claim 12, wherein the adjusting of the LM algorithm is based further on the one or more feedback messages.

15. The apparatus according to claim 12, wherein the process further comprises:

performing a counter-measure to increase the reliability level.

16. The apparatus according to claim 15, wherein the process further comprises:

determining whether the reliability level is below a predetermined threshold, wherein the counter-measure is performed when the reliability level is below the predetermined threshold.

17. The apparatus according to claim 15, wherein the performing of the counter-measure is triggered by one of:

a criticality of one or more feedback messages and a rate of receipt of one or more feedback messages.

18. The apparatus according to claim 15, wherein the counter-measure includes one of:

resetting the LM algorithm and processing the network data using a new LM algorithm.

19. The apparatus according to claim 13, wherein the one or more feedback messages are generated by a user.

20. The apparatus according to claim 13, wherein the process further comprises:

when a number of received feedback messages is greater than a predetermined first threshold, terminating the LM algorithm.

21. The apparatus according to claim 20, wherein the process further comprises:

when the number of received feedback messages is greater than a predetermined second threshold and less than the predetermined first threshold, processing the network data using a new LM algorithm.

22. The apparatus according to claim 21, wherein the process further comprises:

receiving a message indicating the predetermined first threshold and the predetermined second threshold.

23. A tangible non-transitory computer readable medium storing program instructions that cause a computer to execute a process, the process comprising:

processing network data using a Learning Machine (LM) algorithm in a network;

determining results of the processing of network data;

selecting a reliability checking algorithm to determine a reliability level of the results, the reliability checking algorithm being a local reliability checking algorithm or an external reliability checking algorithm;

determining the reliability level of the results using the reliability checking algorithm; and

adjusting the LM algorithm based on the determined reliability level.