Architecture of a hierarchical temporal memory based system

• US 20070192267A1
• Filed: 02/10/2006
• Published: 08/16/2007
• Est. Priority Date: 02/10/2006
• Status: Abandoned Application

• Current Assignee: Numenta, Inc.
• Original Assignee: Numenta, Inc.
• Inventors: Hawkins, Jeffrey, George, Dileep, Astier, Frank, Ahmad, Subutai, Marianetti, Ronald
• Application Number:
  US11/351,437
• Publication Number:
  US 20070192267A1
• 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 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 HTM network executable at least in part on a CPU; and

a first entity arranged to manage a communication between a user application and the part of the HTM network executable on the CPU.

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

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.

3. The system, further comprising:

a server, wherein the server comprises the CPU.

7. A software platform, comprising:

a runtime engine arranged to run an HTM network;

a first interface accessible by a set of tools to at least one of configure, design, train, debug, modify, and deploy the HTM network; and

a second interface accessible to extend a functionality of the runtime engine.

8. The software platform of claim 7, wherein the runtime engine is arranged to distribute operations of the HTM network over a plurality of CPUs.

9. The software platform of claim 7, wherein the runtime engine is arranged to execute operations of the HTM network with a single CPU.

10. The software platform of claim 7, the runtime engine comprising:

a node processing unit arranged to manage at least a portion of the HTM network; and

a supervisor entity arranged to propagate a communication between the set of tools and the node processing unit.

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.

12. The software platform of claim 10, wherein the supervisor entity is dependent on a net list comprising a description of the at least a portion of the HTM network.

13. The software platform of claim 10, 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, wherein the functionality is dynamically extendable by the runtime engine dependent on the second interface.

15. The software platform of claim 7, wherein the set of tools is accessible to a user application, and wherein the set of tools comprises at least one of a configuration tool, a training tool, and a debugging tool.

16. A method of performing operations, comprising:

accessing, via an interface, a computer system capable of running an HTM network; and

at least one of creating, designing, modifying, training, debugging, and deploying the HTM network dependent on the accessing.

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

18. The method of claim 16, further comprising:

accessing a node of the HTM network; and

extending a functionality of the HTM network dependent on the accessing.

19. The method of claim 16, the accessing comprising:

communicating a message between a user application and the interface.

20. The method of claim 16, further comprising:

running the HTM network dependent on instructions provided to the computer system via the interface.