Methods and Apparatus for Transmitting Signals Through Network Elements for Classification

• US 20080071712A1
• Filed: 10/18/2007
• Published: 03/20/2008
• Est. Priority Date: 09/30/2004
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Peck, Charles, Cecchi, Guillermo, Kozloski, James, Rao, Ravishankar
• Application Number:
  US11/874,639
• Publication Number:
  US 20080071712A1
• Time in Patent Office: Days
• US Class Current: 706/20
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]

Abstract

The present invention provides techniques for transmitting at least one signal through an element of a classification system. One or more input signals are received at the element. One or more functional components are extracted from the one or more input signals, and one or more membership components are extracted from the one or more input signals. An output signal is generated from the element comprising a functional component and a membership component that correspond to one or more functional components and membership components from one or more input signals.

Claims

1. A method of transmitting at least one signal through an element of a classification system comprising the steps of:

receiving one or more input signals relating to an image at the element;

extracting one or more functional components from the one or more input signals, wherein the one or more functional components correspond to a classification type;

extracting one or more membership components from the one or more input signals, wherein the one or more membership components correspond to a relationship measure between the one or more input signals and the element; and

generating an output signal for image mapping from the element comprising a functional component and a membership component that correspond to one or more of the functional components and membership components from the one or more input signals, wherein the one or more membership components from the one or more input signals modulate an effect of the one or more functional components from the one or more input signals on the generation of the output signal, and wherein the one or more membership components of the one or more input signals alter the membership component of the output signal.

2. The method of claim 1, further comprising the step of storing in the element a first internal value representing a functional component of the element and a second internal value representing a membership component of the element.

3. The method of claim 1, wherein the step of generating an output signal further comprises the step of:

selecting an arbitrary subset of the one or more input signals comprising one or more functional components and membership components to which the functional component and membership component of the output signal correspond.

4. The method of claim 1, wherein the step of generating an output signal further comprises the step of modifying the output signal through a learning mechanism corresponding to a subset of the one or more input signals.

5. The method of claim 1, wherein the step of generating an output signal further comprises the step of computing a non-linear function of a weighted sum of a subset of the one or more functional components of the one or more input signals in generating the functional component of the output signal.

8. The method of claim 1, wherein, in the step of generating an output signal, the membership component of the output signal comprises a reference time.

9. The method of claim 1, wherein, in the step of generating an output signal, each membership component of the one or more input signals are represented in a plurality of dimensions.

10. The method of claim 1, wherein, in the step of generating an output signal, the membership component is represented by a circular variable.

11. The method of claim 1, wherein, in the step of generating an output signal, the membership component is represented by a phase.

12. The method of claim 1, wherein, in the step of receiving one or more input signals, the one or more input signals comprise at least one feedforward signal and at least one feedback signal.

13. A method of transmitting signals in a network of elements comprising the steps of:

communicating signals relating to an image from each of one or more source elements to at least one destination element in the network of elements, wherein each signal comprises a functional component and a membership component;

generating a new signal for image mapping at each destination element comprising a functional component and a membership component that correspond to one or more functional components and membership components communicated from one or more respective source elements, wherein the membership components from the one or more respective source elements modulate an effect of the functional components from the one or more respective source elements on the generation of the new signal, and wherein the membership components of the one or more respective source elements alter the membership component of the new signal; and

repeating the steps of communicating signals and generating a new signal until one or more final destination elements are reached, wherein a given source element in a next subsequent iteration comprises the destination element in a current iteration, and a communicated signal in the next subsequent iteration comprises the new signal in the current iteration.

14. The method of claim 13, wherein the step of generating a new signal comprises the step of comparing the membership component of the at least one destination element with the membership component of the one or more source elements when the connections between the at least one destination element and the one or more source elements comprise at least two connection types that produce different effects on the functional and membership components of the at least one destination element.

15. The method of claim 13, wherein, in the step of communicating signals, the one or more source elements and at least one destination element each comprise a sub-network of elements extracting different features from an input network.

16. The method of claim 13, wherein the step of repeating the steps of communicating signals further comprises the step of communicating signals through a hierarchy of sub-networks where lower sub-networks extract local features, and higher sub-networks extract global features.

17. The method of claim 13, wherein the step of repeating the steps of communicating signals further comprises the steps of:

activating a decision-making sub-network by the presence of one or more global features; and

comparing functional and membership components of higher and lower sub-networks, such that only those elements in the lower sub-networks with a high functional component and a membership component similar to the membership component of one or more global features in the higher sub-network are selected to be acted upon.

18. Apparatus for transmitting at least one signal through an element of a classification system, comprising:

a memory; and

at least one processor coupled to the memory and operative to;

(i) receive one or more input signals relating to an image at the element;

(ii) extract one or more functional components from the one or more input signals, wherein the one or more functional components correspond to a classification type;

(iii) extract one or more membership components from the one or more input signals, wherein the one or more membership components correspond to a relationship measure between the one or more input signals and the element; and

(iv) generate an output signal for image mapping from the element comprising a functional component and a membership component that correspond to one or more functional components and membership components from the one or more input signals, wherein the one or more membership components from the one or more input signals modulate an effect of the one or more functional components from the one or more input signals on the generation of the output signal, and wherein the one or more membership components of the one or more input signals alter the membership component of the output signal.