USING RADIAL BASIS FUNCTION NETWORKS AND HYPER-CUBES FOR EXCURSION CLASSIFICATION IN SEMI-CONDUCTOR PROCESSING EQUIPMENT

• US 20160162778A1
• Filed: 02/12/2016
• Published: 06/09/2016
• Est. Priority Date: 01/17/2013
• Status: Active Grant

• Current Assignee: Applied Materials Incorporated
• Original Assignee: Applied Materials Incorporated
• Inventors: Cantwell, Dermot
• Granted Patent: US 9,852,371 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/063 using electronic means
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

A method and system for analysis of data, including creating a first node, determining a first hyper-cube for the first node, determining whether a sample resides within the first hyper-cube. If the sample does not reside within the first hyper-cube, the method includes determining whether the sample resides within a first hyper-sphere, wherein the first hyper-sphere has a radius equal to a diagonal of the first hyper-cube.

Claims

1. A method comprising

creating, by a processor, a first node;

determining, by the processor, a first hyper-cube for the first node;

determining, by the processor, whether a sample resides within the first hyper-cube; and

if the sample does not reside within the first hyper-cube, determining, by the processor, whether the sample resides within a first hyper-sphere, wherein the first hyper-sphere has a radius equal to a diagonal of the first hyper-cube.

2. The method of claim 1 further comprising determining a likely sample class based on whether the sample resides within the first hyper-cube or the first hyper-sphere.

3. The method of claim 2 further comprising:

receiving a user-selection of an excursion;

creating an excursion node for the excursion;

determining an excursion hyper-cube for the excursion node;

determining whether the sample resides within the excursion hyper-cube about an excursion node origin;

if the sample does not reside within the excursion hyper-cube, determining whether the sample resides within an excursion hyper-sphere, wherein the excursion hyper-sphere has a radius equal to a diagonal of the excursion hyper-cube; and

determining, by the processor, a likely sample class based on whether the sample resides within the excursion hyper-cube or the excursion hyper-sphere.

4. The method of claim 3 further comprising recording an excursion label for the excursion.

5. The method of claim 3 further comprising determining whether the sample belongs to the first node or the excursion node if the sample is within both the first hyper-sphere and the excursion hyper-sphere.

6. The method of claim 2 further comprising determining a confidence estimation for the sample class.

7. The method of claim 1, wherein creating a first node comprises:

receiving input vector;

receiving activation function; and

determining an activation value of the at least one node.

8. A system comprising:

a memory; and

a processing device coupled to the memory to;

create a first node;

determine a first hyper-cube for the first node;

determine whether a sample resides within the first hyper-cube; and

if the sample does not reside within the first hyper-cube, determine whether the sample resides within a first hyper-sphere, wherein the first hyper-sphere has a radius equal to a diagonal of the first hyper-cube.

9. The system of claim 8, wherein the processing device is further to determine a likely sample class based on whether the sample resides within the first hyper-cube or the first hyper-sphere.

10. The system of claim 9, wherein the processing device is further to:

receive a user-selection of an excursion;

create an excursion node for the excursion;

determine an excursion hyper-cube for the excursion node;

determine whether the sample resides within the excursion hyper-cube about an excursion node origin;

if the sample does not reside within the excursion hyper-cube, determine whether the sample resides within an excursion hyper-sphere, wherein the excursion hyper-sphere has a radius equal to a diagonal of the excursion hyper-cube; and

determine a likely sample class based on whether the sample resides within the excursion hyper-cube or the excursion hyper-sphere.

11. The system of claim 10, wherein the processing device is further to record an excursion label for the excursion.

12. The system of claim 10, wherein the processing device is further to determine whether the sample belongs to the first node or the excursion node if the sample is within both the first hyper-sphere and the excursion hyper-sphere.

13. The system of claim 9, wherein the processing device is further to determine a confidence estimation for the sample class.

14. The system of claim 8, wherein to create a first node, the processing device is to:

receive input vector;

receive activation function; and

determine an activation value of the at least one node.

15. A non-transitory computer-readable storage medium including instructions that, when executed by a computer system, cause the computer system to perform a set of operations comprising:

creating a first node;

determining a first hyper-cube for the first node;

determining whether a sample resides within the first hyper-cube; and

if the sample does not reside within the first hyper-cube, determining whether the sample resides within a first hyper-sphere, wherein the first hyper-sphere has a radius equal to a diagonal of the first hyper-cube.

16. The non-transitory computer-readable storage medium of claim 15, wherein the operations further comprise determining a likely sample class based on whether the sample resides within the first hyper-cube or the first hyper-sphere.

17. The non-transitory computer-readable storage medium of claim 16, wherein the operations further comprise:

receiving a user-selection of an excursion;

creating an excursion node for the excursion;

determining an excursion hyper-cube for the excursion node;

determining whether the sample resides within the excursion hyper-cube about an excursion node origin;

if the sample does not reside within the excursion hyper-cube, determining whether the sample resides within an excursion hyper-sphere, wherein the excursion hyper-sphere has a radius equal to a diagonal of the excursion hyper-cube; and

determining a likely sample class based on whether the sample resides within the excursion hyper-cube or the excursion hyper-sphere.

18. The non-transitory computer-readable storage medium of claim 17, wherein the operations further comprise recording an excursion label for the excursion.

19. The non-transitory computer-readable storage medium of claim 17, wherein the operations further comprise determining whether the sample belongs to the first node or the excursion node if the sample is within both the first hyper-sphere and the excursion hyper-sphere.

20. The non-transitory computer-readable storage medium of claim 15, wherein creating a first node comprises:

receiving input vector;

receiving activation function; and

determining an activation value of the at least one node.