Computer architecture for emulating a bidirectional string correlithm object generator in a correlithm object processing system

Patent metadata

Field	Value
Publication number	US-11263290-B2
Application number	US-201916381926-A
Country	US
Kind code	B2
Filing date	Apr 11, 2019
Priority date	Apr 11, 2019
Publication date	Mar 1, 2022
Grant date	Mar 1, 2022

Abstract

A device configured to emulate a bidirectional string correlithm object generator includes multiple processing stages that operate together to output a bidirectional string correlithm object. The bidirectional string correlithm object includes sub-string correlithm objects that extend in different n-dimensional directions from a central sub-string correlithm object.

First claim

The invention claimed is:

1. A device configured to emulate a bidirectional string correlithm object generator, comprising:
a first processing stage that outputs a first sub-string correlithm object comprising an n-bit digital word, wherein each bit of the n-bit digital word comprises a value of zero or one;
a second processing stage communicatively coupled to the first processing stage and that:
receives the first sub-string correlithm object from the first processing stage;
receives a distance parameter representing a distance in n-dimensional space between adjacent sub-string correlithm objects, the distance parameter identifying a particular number of bits;
for each bit of the first sub-string correlithm object up to the particular number of bits identified by the distance parameter, changes the value from a zero to a one or from a one to a zero; and
outputs a second sub-string correlithm object comprising an n-bit digital word, wherein each bit of the second sub-string correlithm object has a value that is based on the value of a corresponding bit of the first sub-string correlithm object and the changed values for the particular number of bits identified by the distance parameter; and

a third processing stage communicatively coupled to the first processing stage and that:
receives the first sub-string correlithm object from the first processing stage;
receives the distance parameter;
for each bit of the first sub-string correlithm object up to the particular number of bits identified by the distance parameter, changes the value from a zero to a one or from a one to a zero; and
outputs a third sub-string correlithm object comprising an n-bit digital word, wherein each bit of the third sub-string correlithm object has a value that is based on the value of a corresponding bit of the first sub-string correlithm object and the changed values for the particular number of bits identified by the distance parameter.

2. The device of claim 1 , wherein the second processing stage further:
receives the second sub-string correlithm object as feedback from the second processing stage;
for each bit of the second sub-string correlithm object up to the particular number of bits identified by the distance parameter, changes the value from a zero to a one or from a one to a zero; and
outputs a fourth sub-string correlithm object comprising an n-bit digital word, wherein each bit of the fourth sub-string correlithm object has a value that is based on the value of a corresponding bit of the second sub-string correlithm object and the changed values for the particular number of bits identified by the distance parameter.

3. The device of claim 2 , wherein the third processing stage further:
receives the third sub-string correlithm object as feedback from the third processing stage;
for each bit of the third sub-string correlithm object up to the particular number of bits identified by the distance parameter, changes the value from a zero to a one or from a one to a zero; and
outputs a fifth sub-string correlithm object comprising an n-bit digital word, wherein each bit of the fifth sub-string correlithm object has a value that is based on the value of a corresponding bit of the third sub-string correlithm object and the changed values for the particular number of bits identified by the distance parameter.

4. The device of claim 1 , wherein the first processing stage receives a dimension parameter as an input, the dimension parameter identifying the number of dimensions, n, in the n-bit digital word for each sub-string correlithm object.

5. The device of claim 1 , wherein the first sub-string correlithm object, the second sub-string correlithm object, and a third sub-string correlithm object form a first bidirectional string correlithm object in which the first sub-string correlithm object precedes and is adjacent to the second sub-string correlithm object and the first sub-string correlithm object precedes and is adjacent to the third sub-string correlithm object.

6. The device of claim 5 , wherein the first processing stage and the second processing stage are each configured to output additional sub-string correlithm objects based at least in part upon the first sub-string correlithm object to form a second bidirectional string correlithm object that has only the first sub-string correlithm object in common with the first bidirectional string correlithm object.

7. The device of claim 1 , wherein the distance parameter corresponds to one standard deviation of the n-dimensional space.

8. The device of claim 1 , wherein:
the second processing stage successively outputs a subsequent sub-string correlithm object based on changing bit values of the immediately prior sub-string correlithm object received as feedback; and
the third processing stage successively outputs a subsequent sub-string correlithm object based on changing bit values of the immediately prior sub-string correlithm object received as feedback.

9. The device of claim 1 , wherein:
the bits of the first sub-string correlithm object that are changed in value for the second sub-string correlithm object are selected randomly from the n-bit digital word; and
the bits of the first sub-string correlithm object that are changed in value for the third sub-string correlithm object are selected randomly from the n-bit digital word.

10. The device of claim 1 , wherein:
the first sub-string correlithm object has a first core;
the second sub-string correlithm object has a second core;
the third sub-string correlithm object has a third core;
the first core overlaps in n-dimensional space with the second core; and
the first core overlaps in n-dimensional space with the third core.

11. A method for generating a bidirectional string correlithm object, comprising:
outputting at a first processing stage a first sub-string correlithm object comprising an n-bit digital word, wherein each bit of the n-bit digital word comprises a value of zero or one;
receiving the first sub-string correlithm object at a second processing stage;
receiving at the second processing stage a distance parameter representing a distance in n-dimensional space between adjacent sub-string correlithm objects, the distance parameter identifying a particular number of bits;
for each bit of the first sub-string correlithm object up to the particular number of bits identified by the distance parameter, changing the value from a zero to a one or from a one to a zero;
outputting a second sub-string correlithm object comprising an n-bit digital word, wherein each bit of the second sub-string correlithm object has a value that is based on the value of a corresponding bit of the first sub-string correlithm object and the changed values for the particular number of bits identified by the distance parameter;
receiving the first sub-string correlithm object at a third processing stage;
receiving the distance parameter at the third processing stage;
for each bit of the first sub-string correlithm object up to the particular number of bits identified by the distance parameter, changing the value from a zero to a one or from a one to a zero;
outputting a third sub-string correlithm object comprising an n-bit digital word, wherein each bit of the third sub-string correlithm object has a value that is based on the value of a corresponding bit of the first sub-string correlithm object and the changed values for the particular number of bits identified by the distance parameter.

12. The method of claim 11 , further comprising:
receiving at the second processing stage the second sub-string correlithm object as feedback;
for each bit of the second sub-st

Assignees

• Bank Of America

Inventors

• Lawrence Patrick N

Classifications

• G06V10/40 Primary

  Extraction of image or video features · CPC title

• G06V10/7715

  Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06F17/15 Primary

  Correlation function computation {including computation of convolution operations (arithmetic circuits for sum of products per se, e.g. multiply-accumulators G06F7/5443; digital filters, e.g. FIR, IIR, adaptive filters H03H17/00)} · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title