AUTOMATED SEARCH FOR DETECTING PATTERNS AND SEQUENCES IN DATA USING A SPATIAL AND TEMPORAL MEMORY SYSTEM

• US 20130054552A1
• Filed: 08/25/2011
• Published: 02/28/2013
• Est. Priority Date: 08/25/2011
• Status: Active Grant

• Current Assignee: Numenta, Inc.
• Original Assignee: Numenta, Inc.
• Inventors: Hawkins, Jeffrey C., Marianetti, Ronald II, Raj, Anosh, Ahmad, Subutai
• Granted Patent: US 8,504,570 B2
• Time in Patent Office: Days
• US Class Current: 707/706
• CPC Class Codes: G06F 18/285 Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 30/194 References adjustable by an adaptive method, e.g. learning

Abstract

A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.

Claims

1. A method of searching for spatial patterns or temporal sequences of spatial patterns in input data, comprising:

generating a plurality of spatial and temporal memory systems according to configuration information;

providing a coding scheme to each spatial and temporal memory system, wherein each coding scheme comprises a subset of the input data and an encoding to encode the subset of the input data; and

identifying, at each spatial and temporal memory system, spatial patterns or temporal sequences of spatial patterns at the spatial and temporal memory system based on the subset of input data and the encoding.

2. The method of claim 1, wherein one or more provided coding scheme further comprises a time aggregation, wherein spatial patterns or temporal sequences of spatial patterns are further identified at each spatial and temporal memory system based on the time aggregation.

3. The method of claim 1, further comprising:

analyzing a portion of the input data, wherein analyzing the portion of the input data comprises determining at least one of the input data types, the distribution of input data values and the range of input data values.

4. The method of claim 1, wherein providing a coding scheme to each spatial and temporal memory system comprises selecting a coding scheme based on at least one of:

previously searched input data, previously provided coding schemes, analysis of the current input data, and user-selected parameters.

5. The method of claim 1, wherein the configuration information is selected based on at least one of:

previously searched input data, previously generated spatial and temporal memory systems, analysis of the current input data, and user-selected parameters.

6. The method of claim 1, wherein searching for spatial patterns or temporal sequences of spatial patterns occurs independently of user input.

7. The method of claim 1, wherein searching for spatial patterns or temporal sequences of spatial patterns is based on user-selected time and money constraints.

8. The method of claim 1, wherein the spatial patterns and the temporal sequences of spatial patterns are identified by multiple computer processors operating in parallel.

9. The method of claim 1, further comprising:

evaluating the predictive performance of each spatial and temporal memory system; and

generating one or more updated spatial and temporal memory systems or providing one or more updated coding schemes to each spatial and temporal memory system based on the evaluated performance of the spatial and temporal memory systems.

10. The method of claim 9, wherein evaluating the predictive performance comprises determining, for each spatial and temporal memory system, a predicted spatial pattern based on an output of the spatial and temporal memory system, the output generated based on the spatial patterns or temporal sequences of spatial patterns identified at the spatial and temporal memory system.

11. The method of claim 9, further comprising:

ending the identification of spatial patterns or temporal sequences of spatial patterns by a spatial and temporal memory system based on the evaluated performance of the spatial and temporal memory system.

12. The method of claim 1, wherein generating the plurality of spatial and temporal memory systems further comprises:

determining operating parameters for at least one processing node in the spatial and temporal memory system.

13. The method of claim 1, wherein the input data is generated by combining or processing data from more than one data source.

14. A system of searching for spatial patterns or temporal sequences of spatial patterns in input data, comprising:

an automated search engine configured to;

generate a plurality of spatial and temporal memory systems according to configuration information; and

provide a coding scheme to each spatial and temporal memory system, wherein each coding scheme comprises a subset of the input data and an encoding to encode the subset of the input data; and

the plurality of spatial and temporal memory systems configured to identify, at each spatial and temporal memory system, spatial patterns or temporal sequences of spatial patterns at the spatial and temporal memory system based on the subset of input data and the encoding.

15. The system of claim 14, wherein one or more provided coding scheme further comprises a time aggregation, wherein spatial patterns or temporal sequences of spatial patterns are further identified at each spatial and temporal memory system based on the time aggregation.

16. The system of claim 14, further comprising:

an evaluation module further configured to evaluate the predictive performance of each spatial and temporal memory system; and

the automated search engine further configured to generate one or more updated spatial and temporal memory systems or provide one or more updated coding schemes to each spatial and temporal memory system based on the evaluated performance of the spatial and temporal memory systems.

17. The system of claim 16, wherein evaluating the predictive performance comprises determining, for each spatial and temporal memory system, a predicted spatial pattern based on an output of the spatial and temporal memory system, the output generated based on the spatial patterns or temporal sequences of spatial patterns identified at the spatial and temporal memory system.

18. A non-transitory computer-readable storage medium storing executable computer program instructions for searching for spatial patterns or temporal sequences of spatial patterns in input data, the instructions comprising instructions for:

generating a plurality of spatial and temporal memory systems according to configuration information;

providing a coding scheme to each spatial and temporal memory system, wherein each coding scheme comprises a subset of the input data and an encoding to encode the subset of the input data; and

identifying, at each spatial and temporal memory system, spatial patterns or temporal sequences of spatial patterns at the spatial and temporal memory system based on the subset of input data and the encoding of input data.

19. The non-transitory computer-readable storage medium of claim 18, wherein one or more provided coding scheme further comprises a time aggregation, wherein spatial patterns or temporal sequences of spatial patterns are further identified at each spatial and temporal memory system based on the time aggregation.

20. The non-transitory computer-readable storage medium of claim 18, further comprising instructions for:

evaluating the predictive performance of each spatial and temporal memory system; and

generating one or more updated spatial and temporal memory systems or provide one or more updated coding schemes to each spatial and temporal memory system based on the evaluated performance of the spatial and temporal memory systems.