COMPUTER ARCHITECTURE FOR EMULATING CORRELITHM OBJECT DIVERSITY IN A CORRELITHM OBJECT PROCESSING SYSTEM

• US 20190332405A1
• Filed: 04/30/2018
• Published: 10/31/2019
• Est. Priority Date: 04/30/2018
• Status: Active Grant

• Current Assignee: Bank of America Corp.
• Original Assignee: Bank of America Corp.
• Inventors: Lawrence, Patrick N.
• Granted Patent: US 11,010,183 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 17/153 Multidimensional correlation or convolution
• CPC Class Codes: G06F 7/026 Magnitude comparison, i.e. determining the relative order of operands based on their numerical value, e.g. window comparator
• CPC Class Codes: G06F 9/45508 Runtime interpretation or emulation, e g. emulator loops, bytecode interpretation
• CPC Class Codes: G06N 20/20 Ensemble learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

A system that includes an edge node configured to define a first set of correlithm objects for the first device and to send the first set of correlithm objects to the first device. The first set of correlithm objects includes a first correlithm object within a core distance of a root correlithm from the set of root correlithm objects. The core distance identifies the maximum number of different bits between the root correlithm object and a correlithm object. The edge node is further configured to define a second set of correlithm objects for the second device and to send the second set of correlithm objects to the second device. The second set of input correlithm objects comprises a second correlithm within the core distance of the root correlithm object from the set of root correlithm objects. The first correlithm object and the second correlithm object are different.

Claims

1. A system configured to emulate a correlithm object processing system, comprising one or more devices configured to implement a network of nodes comprising:

a memory operable to store a node table that identifies;

a set of root correlithm objects, wherein each root correlithm object in the set of root correlithm objects is an n-bit digital word of binary values; and

a set of output correlithm objects corresponding with the set of root correlithm objects, wherein each output correlithm object in the set of output correlithm objects is an n-bit digital word of binary values; and

an edge node in signal communication with the memory, a first device, and a second device, wherein the edge node is configured to;

define a first set of correlithm objects for the first device, wherein;

the first set of correlithm objects comprises a first correlithm object within a core distance of a root correlithm from the set of root correlithm objects; and

the core distance identifies the maximum number of different bits between the root correlithm object and a correlithm object;

send the first set of correlithm objects to the first device;

define a second set of correlithm objects for the second device, wherein;

the second set of input correlithm objects comprises a second correlithm within the core distance of the root correlithm object from the set of root correlithm objects; and

the first correlithm object and the second correlithm object are different; and

send the second set of correlithm objects to the second device.

2. The system of claim 1, further comprising an interior node, wherein:

the interior node is not in signal communication with devices outside of the network; and

the edge node is further configured to;

receive a correlithm object from the first device;

determine distances between the received correlithm object and each root correlithm object in the node table, wherein the distance between the received correlithm object and a root correlithm object is based on differences between a digital word representing the received correlithm object and digital words representing each of the root correlithm objects;

identify a root correlithm object from the node table with the shortest distance;

fetch an output correlithm object from the node table linked with the identified root correlithm object; and

send the output correlithm object to the interior node.

3. The system of claim 2, wherein determining distances between the received correlithm object and each root correlithm object in the node table comprises determining a Hamming distance between the received correlithm object and a root correlithm object in the first node table.

4. The system of claim 2, wherein determining distances between the received correlithm object and each root correlithm object in the node table comprises:

performing an XOR operation between the received correlithm object and an input correlithm object in the first node table to generate a binary string; and

counting the number of logical high values in the binary string, wherein the number of logical high values corresponds with a distance.

5. The system of claim 1, wherein the core distance is equal to at least one standard deviation away from half the number of bits in the n-bit digital word used to represent a root correlithm object.

6. The system of claim 1, wherein the core distance is value equal to at least two standard deviation away from half the number of bits in the n-bit digital word used to represent a root correlithm object.

7. The system of claim 1, wherein the core distance is value equal to at least six standard deviation away from half the number of bits in the n-bit digital word used to represent a root correlithm object.

8. A correlithm object generating method, comprising:

accessing, by a first device, a node table that identifies;

a set of root correlithm objects, wherein each root correlithm object in the set of root correlithm objects is an n-bit digital word of binary values; and

a set of output correlithm objects corresponding with the set of root correlithm objects, wherein each output correlithm object in the set of output correlithm objects is an n-bit digital word of binary values;

defining, by the first device, a first set of correlithm objects for a second device, wherein;

the first set of correlithm objects comprises a first correlithm object within a core distance of a root correlithm from the set of root correlithm objects; and

the core distance identifies the maximum number of different bits between the root correlithm object and a correlithm object;

sending, by the first device, the first set of correlithm objects to the second device;

defining, by the first device, a second set of correlithm objects for a third device, wherein;

the second set of input correlithm objects comprises a second correlithm within the core distance of the root correlithm object from the set of root correlithm objects; and

the first correlithm object and the second correlithm object are different; and

sending, by the first device, the second set of correlithm objects to the third device.

9. The method of claim 8, further comprising:

receiving, by the first device, a correlithm object from the second device;

determining, by the first device, distances between the received correlithm object and each root correlithm object in the node table, wherein the distance between the received correlithm object and a root correlithm object is based on differences between a digital word representing the received correlithm object and digital words representing each of the root correlithm objects;

identifying, by the first device, a root correlithm object from the node table with the shortest distance;

fetching, by the first device, an output correlithm object from the node table linked with the identified root correlithm object; and

sending, by the first device, the output correlithm object to an interior node, wherein the interior node is not in signal communication with devices outside of the network

10. The method of claim 9, wherein determining distances between the received correlithm object and each root correlithm object in the node table comprises determining a Hamming distance between the received correlithm object and a root correlithm object in the first node table.

11. The method of claim 9, wherein determining distances between the received correlithm object and each root correlithm object in the node table comprises:

performing an XOR operation between the received correlithm object and an input correlithm object in the first node table to generate a binary string; and

counting the number of logical high values in the binary string, wherein the number of logical high values corresponds with a distance.

12. The method of claim 8, wherein the core distance is equal to at least one standard deviation away from half the number of bits in the n-bit digital word used to represent a root correlithm object.

13. The method of claim 8, wherein the core distance is value equal to at least two standard deviation away from half the number of bits in the n-bit digital word used to represent a root correlithm object.

14. The method of claim 8, wherein the core distance is value equal to at least six standard deviation away from half the number of bits in the n-bit digital word used to represent a root correlithm object.

15. A device configured to emulate a correlithm object processing system, comprising:

a network interface in signal communication with a first device and a second device;

a memory operable to store a node table that identifies;

a set of root correlithm objects, wherein each root correlithm object in the set of root correlithm objects is an n-bit digital word of binary values; and

a set of output correlithm objects corresponding with the set of root correlithm objects, wherein each output correlithm object in the set of output correlithm objects is an n-bit digital word of binary values; and

an node engine implemented by a processor in signal communication with the network interface and the memory, configured to;

define a first set of correlithm objects for the first device, wherein;

the first set of correlithm objects comprises a first correlithm object within a core distance of a root correlithm from the set of root correlithm objects; and

the core distance identifies the maximum number of different bits between the root correlithm object and a correlithm object;

send the first set of correlithm objects to the first device;

define a second set of correlithm objects for the second device, wherein;

the second set of input correlithm objects comprises a second correlithm within the core distance of the root correlithm object from the set of root correlithm objects; and

the first correlithm object and the second correlithm object are different; and

send the second set of correlithm objects to the second device.

16. The device of claim 15, the node engine is further configured to:

receive a correlithm object from the first device via the network interface;

determine distances between the received correlithm object and each root correlithm object in the node table, wherein the distance between the received correlithm object and a root correlithm object is based on differences between a digital word representing the received correlithm object and digital words representing each of the root correlithm objects;

identify a root correlithm object from the node table with the shortest distance;

fetch an output correlithm object from the node table linked with the identified root correlithm object; and

send the output correlithm object to an interior node, wherein the interior node is not in signal communication with devices outside of the network.

17. The device of claim 16, wherein determining distances between the received correlithm object and each root correlithm object in the node table comprises determining a Hamming distance between the received correlithm object and a root correlithm object in the first node table.

18. The device of claim 16, wherein determining distances between the received correlithm object and each root correlithm object in the node table comprises:

performing an XOR operation between the received correlithm object and an input correlithm object in the first node table to generate a binary string; and

counting the number of logical high values in the binary string, wherein the number of logical high values corresponds with a distance.

19. The device of claim 15, wherein the core distance is equal to at least one standard deviation away from half the number of bits in the n-bit digital word used to represent a root correlithm object.

20. The device of claim 15, wherein the core distance is value equal to at least six standard deviation away from half the number of bits in the n-bit digital word used to represent a root correlithm object.