Pattern categoritzation system having self-organizing analog fields

• US 5,493,688 A
• Filed: 01/11/1993
• Issued: 02/20/1996
• Est. Priority Date: 07/05/1991
• Status: Expired due to Fees

• Current Assignee: BOOZ Allen & Hamilton Incorporated (BOOZ Allen Hamilton Holding Corporation)
• Original Assignee: BOOZ Allen & Hamilton Incorporated (BOOZ Allen Hamilton Holding Corporation)
• Inventors: Weingard, Fred S.
• Primary Examiner(s): Razavi, Michael T.
• Assistant Examiner(s): NOT, DEFINED
• Application Number:
  US08/002,155
• Time in Patent Office: 1,135 Days
• Field of Search: 382/14, 382/15, 382/36, 382/156, 382/157, 382/158, 395/20, 395/23, 364/715.06
• US Class Current: 382/157
• CPC Class Codes: B82Y 30/00 Nanotechnology for materials or surface science, e.g. nanocomposites
• CPC Class Codes: G06F 18/2137 based on criteria of topology preservation, e.g. multidimensional scaling or self-organising maps
• CPC Class Codes: G06F 18/2433 Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology

Abstract

Pattern categorization is provided by a self-organizing analog field/layer which learns many-to-many, analog spatiotemporal mappings. The field/layer employs a set of input nodes, each input node having two long term memory weights, and a set of output nodes. Each input node is for categorizing patterns with respect to a plurality of categories. The long term memory weights of an input node encode the patterns categorized by the input node. Each input node generates signals as a function of respective long term memory weights and input signals to the input node. Each input node is coupled to a different output node. Each output node receives signals generated by the respective input node and selects a category of the respective input node. The output nodes provide a mapping between plural parts of the input pattern and plural categories of the input nodes. Category selections of the output nodes are modified such that sum of the output signals from the output nodes is within a predefined range. Upon the sum of the output signals being within the predefined range, the output nodes provide categorization of the input pattern from the mapping between plural parts of the input pattern and plural categories of the input nodes.

Claims

1. A pattern categorization system comprising:

a presentation field for presenting input signals defining an input pattern;

a plurality of input nodes, each for categorizing patterns with respect to a plurality of categories, the input nodes being coupled to the presentation field for receiving the input signals, for each input signal received by an input node, the input node having two weights having a respective value, the weights being indicative of a plurality of patterns categorized by the input node such that a net signal is generated as a function of the weights and input signals to the input node, and the net signal is indicative of similarity between the input pattern and patterns categorized by the input node;

a plurality of output nodes, one for each input node such that a different input node is connected to a different output node and each output node receives the net signal from the respective input node, and in response to the respective received net signal each output node selecting a category of the corresponding input node such that the output nodes provide a mapping between plural parts of the input pattern and plural categories, each output node providing an output signal indicative of category selection;

a modulation mechanism coupled between the output nodes and the input nodes, for modifying category selections of the output nodes by modulating the input nodes with a modulation signal such that the sum of the output signals from the output nodes is within a predefined range, upon the sum of the output signals being within the predefined range, the output nodes providing categorization of the input pattern from the mapping between plural parts of the input pattern and plural categories of the input nodes; and

for each weight of the input nodes, a learning mechanism for adapting the respective value of each weight to an exact analytical value in response to the modulation signal.

2. A system as recited in claim 1 wherein the system is unsupervised.

3. A system as recited in claim 1 wherein the mapping is many-to-many mapping.

4. A system as recited in claim 1 wherein for each input node a weight of the input node controls generalization of spatiotemporal parts of the input patterns.

5. A system as recited in claim 1 wherein for each input node a weight of the input node controls strength of the input signal to the input node, the strength of the input signal being indicated both as a degree of connectivity from the presentation field to the input node, and as a shaping factor generalization of spatiotemporal parts of the input pattern.

6. A system as recited in claim 5 wherein the degree of connectivity is in the range of 0 to 1, 0 indicating absence of connection between the presentation field and the input node, and 1 indicating relative strength of connection between the presentation field and the input node.

7. A system as recited in claim 1 wherein the predefined range is between 0 and the number of input nodes in the plurality of input nodes.

8. A system as recited in claim 7 wherein the predefined range is a real number.