Architecture of a Hierarchical Temporal Memory Based System

• US 20080183647A1
• Filed: 04/14/2008
• Published: 07/31/2008
• Est. Priority Date: 02/10/2006
• Status: Active Grant

• Current Assignee: Numenta, Inc.
• Original Assignee: Numenta, Inc.
• Inventors: Marianetti, Ronald, Hawkins, Jeffrey, George, Dileep, Astier, Frank, Ahmad, Subutai
• Granted Patent: US 8,447,711 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• 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 hierarchical temporal memory (HTM) based system may be provided as a software platform. The software platform includes: a runtime engine arranged to run an HTM network; a first interface accessible by a set of tools to configure, design, modify, train, debug, and/or deploy the HTM network; and a second interface accessible to extend a functionality of the runtime engine.

Claims

1. A system, comprising:

an Hierarchical Temporal Memory (HTM) network executable at least in part on a CPU, the HTM network comprising;

a first node for receiving an input data representing an object or a status of an object and generating a first vector representing information about patterns and sequences in the input data corresponding to learned patterns and sequences; and

a second node associated with the first node to generate and outputting a second vector based on the first vector, the second vector representing information about causes of the input data; and

a supervisor entity associated with the HTM network for managing communication between a user application and the HTM network.

2. The system of claim 1, wherein the supervisor entity is instantiated at least in part in software.

3. The system of claim 1, wherein the HTM network is implemented on a server including one or more central processing units (CPUs).

4. The system of claim 1, wherein the communication comprises an XML-encoded message.

5. The system of claim 1, wherein the communication is transmitted using at least one of an HTTP and an HTTPS protocol.

6. The system of claim 1, wherein the HTM network is executable across a plurality of CPUs.

7. A software platform, comprising:

an Hierarchical Temporal Memory (HTM) network comprising;

a first node for receiving an input data representing an object or a status of an object and generating a first vector representing information about patterns and sequences in the input data corresponding to learned patterns and sequences; and

a second node associated with the first node to generate and output a second vector based on the first vector, the second vector representing information about causes of the input data; and

a supervisor entity associated with the HTM network for managing the HTM network.

8. The software platform of claim 7, wherein the HTM network is distributed over a plurality of CPUs.

9. The software platform of claim 7, wherein the HTM network is operated with a single CPU.

10. The software platform of claim 7 further comprising:

a node processing unit for managing at least a portion of the HTM network.

11. The software platform of claim 10, wherein the node processing unit is allocated to a CPU running the at least a portion of the HTM network to manage a portion of the HTM network running on the CPU.

12. The software platform of claim 7, wherein the supervisor entity comprises a net list for describing a configuration of the HTM network.

13. The software platform of claim 7, wherein the supervisor entity is arranged to allocate the at least a portion of the HTM network to a CPU.

14. The software platform of claim 7 further comprising a node plug-in interface for dynamically extending functionality of the HTM network.

15. The software platform of claim 7 further comprising a configuration tool associated with the supervisor entity for configuring the HTM network, and a training tool associated with the supervisor entity for training the HTM network.

16. A method of operating an Hierarchical Temporal Memory (HTM) network, comprising:

creating the HTM network at least partly on a first computer system, via a supervisor entity provided on the first computer system for managing the HTM network, the HTM network comprising a first node for receiving an input data representing an object or a status of the object and generating a first vector representing information about patterns and sequences in the input data corresponding to learned patterns and sequences and a second node associated with the first node to generate a second vector based on the first vector, the second vector representing information about causes of the input data;

modifying a configuration of the created HTM network via the supervisor entity;

training the created or modified HTM network via the supervisor entity; and

outputting the second vector to a user application via the supervisor entity

17. The method of claim 16, wherein the first computer system comprises a plurality of CPUs.

18. The method of claim 16, further comprising:

extending a functionality of the HTM network by providing a node plug-in interface for associating a third node with the first node or the second node, the third node provided on a second computing system.

19. The method of claim 16 further comprising:

communicating a message between a user application and the supervisor entity.

20. The method of claim 16, further comprising:

running the HTM network responsive to instructions provided to the computer system via the supervisor entity.

21. 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 a computing module in the first level is configured to output to the computing module in the second level a first set of values representing information about possible causes of input data received by the system, and

wherein the computing module in the second level is configured to determine a possible cause of the input data received by the system dependent on the set of values output by the computing module in the first level.

22. 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 a computing module in the first level is configured to output to the computing module in the second level a first set of values representing information about possible causes of input data received by the system, and

wherein the computing module in the second level is configured to determine a second set of values representing information about possible causes of the input data received by the system.

23. A computer-implemented method, comprising:

running a network of a hierarchy of computing modules configured to learn a cause of a first set of input data received over space and time and further configured to determine a cause of a second set of input data dependent on the learned cause, wherein running the network comprises;

processing a plurality of entities of the network according to a priority associated with each of the entities, at least one entities implemented using a base class, wherein at least one of the entities is extensible; and

compiling source code for the network, wherein the source code comprises source code for a subclass extending the base class.

24. A computer-implemented method, comprising:

running a network of a hierarchy of computing modules configured to learn a cause of a first set of input data received over space and time and further configured to determine a cause of a second set of input data dependent on the learned cause, wherein running the network comprises;

processing a plurality of entities of the network according to a priority associated with each of the entities, at least one entities implemented using a base class, wherein at least one of the entities is extensible; and

dynamically linking a library during operation of the network, wherein the library comprises code for extending the base class.

25. A method of performing operations, comprising:

receiving data caused by a manifestation of a behavior;

learning a cause of the received data and forming a representation of the behavior;

associating the representation with a mechanism that generates the behavior; and

causing the behavior to occur using the mechanism.

26. The method of claim 25, wherein the mechanism comprises at least one of a motor and processing circuitry.

27. 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 dependent on a spatial similarity between the first pattern and the second pattern.

28. 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 dependent on a temporal relationship between the first pattern and the second pattern.

29. A computer-readable medium having instructions stored therein that are executable on a processor, the instructions comprising instructions to:

input spatial patterns in sensed input data, wherein spatial patterns received over time represent sequences;

identify received sequences that occur frequently according to a predetermined statistical threshold; and

output a distribution representing information about the statistically frequent sequences being a cause of the sensed input data, wherein the distribution is generated over a set of previously learned causes.

30. The computer-readable medium of claim 29, further comprising instructions to:

store a count of how many times a particular sequence has been received.

31. 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,

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, and

wherein the subset is determined dependent on a control signal received by the computing module in the first level.

32. The system of claim 31, 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.

33. 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 operates on a first server, and wherein the at least one computing module in the second level operates on a second server; and

at least one message manager module configured to relay information between the first server and the second server, wherein the message manager module is further configured to operate according to at least one of a message passing interface (MPI) protocol and a zero-copy protocol using shared memory.

34. 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 operates on a first server, and wherein the at least one computing module in the second level operates on a second server; and

at least one message manager module configured to relay information between the first server and the second server, wherein the message manager module is further configured to operate dependent on at least one of a socket connection and a shared memory buffer.