POOLING IN A HIERARCHICAL TEMPORAL MEMORY BASED SYSTEM

• US 20070192270A1
• 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 7,613,675 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• 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. The hierarchy is further configured to associate a first pattern in the input data and a second pattern in the input data to a same possible cause of the 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,

wherein the hierarchy is further configured to associate a first pattern in the input data and a second pattern in the input data to a same possible cause of the input data.

2. The system of claim 1, wherein the hierarchy is further configured to associate the first pattern and the second pattern to the same possible cause dependent on a spatial similarity between the first pattern and the second pattern.

3. The system of claim 1, wherein the hierarchy is further configured to associate the first pattern and the second pattern to the same possible cause dependent on a temporal relationship between the first pattern and the second pattern.

4. The system of claim 3, wherein the temporal relationship comprises an order in which the first pattern and the second pattern are received in the hierarchy.

5. The system of claim 3, wherein the temporal relationship comprises a rhythm at which the first pattern and the second pattern are received in the hierarchy.

6. The system of claim 3, wherein the temporal relationship comprises a tempo at which the first pattern and the second pattern are received in the hierarchy.

7. The system of claim 1, wherein at least one of the first pattern and the second pattern was previously learned by the hierarchy.

8. The system of claim 1, wherein the hierarchy comprises a first level of computing modules and a second level of at least one computing module, wherein the first pattern and the second pattern are received by at least one of the computing modules in the first level and are associated to the same possible cause dependent on a control signal from the computing module in the second level.

9. The system of claim 8, wherein the computing module in the second level has an input range greater than an input range of the computing module in the first level.

10. The system of claim 1, wherein at least part of the hierarchy is implemented in at least one of software and hardware.

11. A computer-implemented method of performing operations, comprising:

learning a cause of a first set of input data received over space and time by a hierarchy of computing modules, wherein the hierarchy is capable of determining a cause of a second set of input data dependent on the learned cause, and wherein the learning comprises;

associating a first pattern in the first set of input data and a second pattern in the first set of input data to a same possible cause of the first set of input data.

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

associating the first pattern and the second pattern to the same possible cause dependent on a spatial similarity between the first pattern and the second pattern.

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

associating the first pattern and the second pattern to the same possible cause dependent on a temporal relationship between the first pattern and the second pattern.

14. The computer-implemented method of claim 13, wherein the temporal relationship comprises an order in which the first pattern and the second pattern are received in the hierarchy.

15. The computer-implemented method of claim 13, wherein the temporal relationship comprises a rhythm at which the first pattern and the second pattern are received in the hierarchy.

16. The computer-implemented method of claim 13, wherein the temporal relationship comprises a tempo at which the first pattern and the second pattern are received in the hierarchy.

17. The computer-implemented method of claim 11, wherein at least one of the first pattern and the second pattern was previously learned by the hierarchy.

18. The computer-implemented method of claim 11, wherein the hierarchy comprises a first level of computing modules and a second level of at least one computing module, the method further comprising:

receiving the first pattern and the second pattern by at least one of the computing modules in the first level; and

associating the first pattern and the second pattern to the same possible cause dependent on a control signal generated from the computing module in the second level.

19. 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, wherein the hierarchy is capable of determining a cause of a second set of input data dependent on the learned cause, and wherein the instructions to learn comprises instructions to;

associate a first pattern in the first set of input data and a second pattern in the first set of input data to a same possible cause of the first set of input data.

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

associate the first pattern and the second pattern to the same possible cause dependent on a spatial similarity between the first pattern and the second pattern.

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

associate the first pattern and the second pattern to the same possible cause dependent on a temporal relationship between the first pattern and the second pattern.

22. The computer-readable medium of claim 21, wherein the temporal relationship comprises an order in which the first pattern and the second pattern are received in the hierarchy.

23. The computer-readable medium of claim 21, wherein the temporal relationship comprises a rhythm at which the first pattern and the second pattern are received in the hierarchy.

24. The computer-readable medium of claim 21, wherein the temporal relationship comprises a tempo at which the first pattern and the second pattern are received in the hierarchy.

25. The computer-readable medium of claim 19, wherein at least one of the first pattern and the second pattern was previously learned by the hierarchy.

26. The computer-readable medium of claim 19, wherein the hierarchy comprises a first level of computing modules and a second level of at least one computing module, the instructions further comprising instructions to:

receive the first pattern and the second pattern by at least one of the computing modules in the first level; and

associate the first pattern and the second pattern to the same possible cause dependent on a control signal generated from the computing module in the second level.