ATTENTION IN A HIERARCHICAL TEMPORAL MEMORY BASED SYSTEM

• US 20070192264A1
• Filed: 01/11/2007
• Published: 08/16/2007
• Est. Priority Date: 02/10/2006
• Status: Active Grant

• Current Assignee: Numenta, Inc.
• Original Assignee: Numenta, Inc.
• Inventors: Hawkins, Jeffrey, George, Dileep
• Granted Patent: US 7,624,085 B2
• Time in Patent Office: Days
• US Class Current: 706/15
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/047 Probabilistic or stochastic networks
• CPC Class Codes: G06N 3/049 Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A hierarchy of computing modules is configured to learn a cause of input data sensed over space and time, and is further configured to determine a cause of novel sensed input data dependent on the learned cause. Further, the hierarchy has a first level of computing modules and a second level of at least one computing module, where at least one of the computing modules in the first level is configured to receive a portion of the novel sensed input data, and where the computing module in the first level is further capable of determining a possible cause of the novel sensed input data dependent on analyzing only a subset of the portion of the novel sensed input data.

Claims

1. A system, comprising:

a hierarchy of computing modules configured to learn a cause of input data sensed over space and time, the hierarchy further configured to determine a cause of novel sensed input data dependent on the learned cause, and the hierarchy having a first level of computing modules and a second level of at least one computing module,

wherein at least one of the computing modules in the first level is configured to receive a portion of the novel sensed input data, and

wherein the computing module in the first level is further capable of determining a possible cause of the novel sensed input data dependent on analyzing only a subset of the portion of the novel sensed input data.

2. The system of claim 1, wherein the computing module in the first level is further configured to receive the portion of the novel sensed input data across an input range of the computing module in the first level.

3. The system of claim 2, wherein the subset is received from a portion of the input range.

4. The system of claim 1, wherein the subset is determined dependent on a control signal received by the computing module in the first level.

5. The system of claim 4, wherein the control signal is generated by the computing module in the second level, wherein an input range of the computing module in the second level is greater than an input range of the computing module in the first level.

6. The system of claim 4, wherein the control signal is generated externally.

7. The system of claim 4, wherein the control signal indicates at least one category of causes to be analyzed by the computing module in the first level when determining a possible cause of the novel sensed input data.

8. The system of claim 1, wherein at least one of the computing module in the first level and the computing module in the second level is implemented at least in part in at least one of software and hardware.

9. The system of claim 1, wherein an input range of the computing module in the second level is greater than an input range of the computing module in the first level.

10. A computer-implemented method of recognizing an object, comprising:

learning a cause of a first set of input data received over space and time by a hierarchy of computing modules having a first level of a plurality of computing modules and a second level of at least one computing module;

receiving a portion of a second set of input data at one of the computing modules in the first level; and

determining a possible cause of the second set of input data dependent on analyzing a subset of the portion of the second set of input data received at the computing module in the first level.

11. The computer-implemented method of claim 10, further comprising:

receiving the portion of the second set of input data across an input range of the computing module in the first level.

12. The computer-implemented method of claim 11, wherein the subset is received from a portion of the input range.

13. The computer-implemented method of claim 10, further comprising:

receiving a control signal at the computing module in the first level, wherein the subset is determined dependent on the control signal.

14. The computer-implemented method of claim 13, wherein the control signal is generated by the computing module in the second level, wherein an input range of the computing module in the second level is greater than an input range of the computing module in the first level.

15. The computer-implemented method of claim 13, wherein the control signal is generated externally.

16. The computer-implemented method of claim 13, wherein the control signal indicates at least one category of causes to be analyzed by the computing module in the first level when determining a possible cause of the second set of input data.

17. The computer-implemented method of claim 10, wherein an input range of the computing module in the second level is greater than an input range of the computing module in the first level.

18. A computer-readable medium having instructions therein that are executable by a processor, the instructions comprising instructions to:

learn a cause of a first set of input data received over space and time by a hierarchy of computing modules having a first level of a plurality of computing modules and a second level of at least one computing module;

receive a portion of a second set of input data at one of the computing modules in the first level; and

determine a possible cause of the second set of input data dependent on analyzing a subset of the portion of the second set of input data received at the computing module in the first level.

19. The computer-readable medium of claim 18, further comprising instructions to:

receive the portion of the second set of input data across an input range of the computing module in the first level.

20. The computer-readable medium of claim 19, wherein the subset is received from a portion of the input range.

21. The computer-readable medium of claim 18, further comprising instructions to:

receive a control signal at the computing module in the first level, wherein the subset is determined dependent on the control signal.

22. The computer-readable medium of claim 21, wherein the control signal is generated by the computing module in the second level, wherein an input range of the computing module in the second level is greater than an input range of the computing module in the first level.

23. The computer-readable medium of claim 21, wherein the control signal is generated externally.

24. The computer-readable medium of claim 21, wherein the control signal indicates at least one category of causes to be analyzed by the computing module in the first level when determining a possible cause of the second set of input data.

25. The computer-readable medium of claim 18, wherein an input range of the computing module in the second level is greater than an input range of the computing module in the first level.