US5638491A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for hierarchical input classification using a neural network
Assignee: United Parcel Service of America Inc
•
Filing: 1995-01-23
•
Granted: 1997-06-10
•
Expires: 2015-01-23
Abstract
Abstract An input is classified into one of a plurality of possible outputs. A top-level classifier generates an approximate identification for the input as one of the possible outputs and selects two or more neural networks corresponding to the approximate identification. The selected neural networks generate two or more identifications for the input as one or more of the possible outputs. A postprocessor classifies the input as one of the possible outputs in accordance with the two or more identifications of the selected neural networks. According to an alternative embodiment, a top-level classifier selects a subset of neurons of a neural network and the subset of neurons identifies the input as one of the possible outputs.
Inventors
- 👤 Michael C. Moed
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-10 01:41
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/19; G06V30/191; G06V30/19107; G06F; G06F18/00; G06F18/20; G06F18/23; G06F18/232; G06F18/2321; G06F18/23213; G06F18/24; G06F18/241; G06F18/2413; G06F18/24133; G06F18/24137; G06F18/2414; G06F18/24143; G06V30/19173
Claims Analysis
Total Claims: 21
Claim 1
Independent Claim
98 words
A method for classifying an input into one of a plurality of possible outputs, comprising the steps of: (a) applying a top-level classifier to the input to generate an approximate identification for the input as one of the possible outputs; (b) using the approximate identification to select a subset of available cluster classifiers; (c) applying said selected cluster classifiers to the input to generate two or more identifications for the input as one or more of the possible outputs; and (d) classifying the input as one of the possible outputs in accordance with said two or more identifications.
Claim 2
Independent Claim
98 words
A method for classifying an input into one of a plurality of possible outputs, comprising the steps of: (a) applying a top-level classifier to the input to generate an approximate identification for the input as one of the possible outputs; (b) using the approximate identification to select a subset of available cluster classifiers; (c) applying said selected cluster classifiers to the input to generate two or more identifications for the input as one or more of the possible outputs; and (d) classifying the input as one of the possible outputs in accordance with said two or more identifications.
Claim 3
Dependent Claim
28 words
The method of claim 1, wherein: each of the cluster classifiers employs one or more neurons; and at least two of the cluster classifiers share a common output.
Claim 4
Dependent Claim
15 words
The method of claim 1, wherein step (a) comprises the step of implementing K-means clustering.
Claim 5
Dependent Claim
29 words
The method of claim 1, wherein at least one of the cluster classifiers is based on a feature space different from at least one other of the cluster classifiers.
Claim 6
Dependent Claim
12 words
The method of claim 1, wherein the input corresponds to a character.
Claim 7
Dependent Claim
22 words
The method of claim 1, wherein the top-level classifier and each of the cluster classifiers are associated with the same feature space.
Claim 8
Independent Claim
103 words
A system for classifying an input into one of a plurality of possible outputs, comprising: (a) means for applying a top-level classifier to the input to generate an approximate identification for the input as one of the possible outputs; (b) means for using the approximate identification to select a subset of available cluster classifiers; (c) means for applying said selected cluster classifiers to the input to generate two or more identifications for the input as one or more of the possible outputs; and (d) means for classifying the input as one of the possible outputs in accordance with said two or more identifications.
Claim 9
Independent Claim
103 words
A system for classifying an input into one of a plurality of possible outputs, comprising: (a) means for applying a top-level classifier to the input to generate an approximate identification for the input as one of the possible outputs; (b) means for using the approximate identification to select a subset of available cluster classifiers; (c) means for applying said selected cluster classifiers to the input to generate two or more identifications for the input as one or more of the possible outputs; and (d) means for classifying the input as one of the possible outputs in accordance with said two or more identifications.
Claim 10
Dependent Claim
26 words
The system of claim 7, wherein: each of the cluster classifiers employs one or more neurons; and at least two of the share a common output.
Claim 11
Dependent Claim
14 words
The system of claim 7, wherein means (a) comprises means for implementing K-means clustering.
Claim 12
Dependent Claim
29 words
The system of claim 7, wherein at least one of the cluster classifiers is based on a feature space different from at least one other of the cluster classifiers.
Claim 13
Dependent Claim
12 words
The system of claim 7, wherein the input corresponds to a character.
Claim 14
Dependent Claim
22 words
The system of claim 7, wherein the top-level classifier and each of the cluster classifiers are associated with the same feature space.
Claim 15
Independent Claim
103 words
A system for classifying an input into one of a plurality of possible outputs, comprising: (a) a top-level classifier; (b) a plurality of cluster classifiers; and (c) a postprocessor, wherein: the top-level classifier generates an approximate identification for the input as one of the possible outputs and uses the approximate identification to select a subset of the cluster classifiers; the selected cluster classifiers generate two or more identifications for the input as one or more of the possible outputs; and the postprocessor classifies the input as one of the possible outputs in accordance with the two or more identifications of the cluster classifiers.
Claim 16
Independent Claim
103 words
A system for classifying an input into one of a plurality of possible outputs, comprising: (a) a top-level classifier; (b) a plurality of cluster classifiers; and (c) a postprocessor, wherein: the top-level classifier generates an approximate identification for the input as one of the possible outputs and uses the approximate identification to select a subset of the cluster classifiers; the selected cluster classifiers generate two or more identifications for the input as one or more of the possible outputs; and the postprocessor classifies the input as one of the possible outputs in accordance with the two or more identifications of the cluster classifiers.
Claim 17
Dependent Claim
28 words
The system of claim 13, wherein: each of the cluster classifiers comprises one or more neurons; and at least two of the cluster classifiers share a common output.
Claim 18
Dependent Claim
12 words
The system of claim 13, wherein the top-level classifier implements K-means clustering.
Claim 19
Dependent Claim
29 words
The system of claim 13, wherein at least one of the cluster classifiers is based on a feature space different from at least one other of the cluster classifiers.
Claim 20
Dependent Claim
12 words
The system of claim 13, wherein the input corresponds to a character.
Claim 21
Dependent Claim
22 words
The system of claim 13, wherein the top-level classifier and each of the cluster classifiers are associated with the same feature space.
References Cited (Backward Citations)
US3701095A
Cited
US3950733A
Cited
US4044243A
Cited
US4326259A
Cited
US4599698A
Cited
US4599693A
Cited
US5054093A
Cited
JPS62133589A
Cited
JPH0233687A
Cited
US5010512A
Cited
US5297237A
Cited
US4954963A
Cited
US5293454A
Cited
JPH02238588A
Cited
US5033006A
Cited
US5119438A
Cited
JPH02242392A
Cited
US5140530A
Cited
JPH02300876A
Cited
US5060278A
Cited
US5086479A
Cited
US5150323A
Cited
US5426745A
Cited
US5339818A
Cited
US5067164A
Cited
US5311601A
Cited
US5220618A
Cited
US5218646A
Cited
US5299284A
Cited
US5245697A
Cited
US5175796A
Cited
US5058180A
Cited
US5181171A
Cited
US5214744A
Cited
US5247584A
Cited
US5214715A
Cited
US5479575A
Cited
US5239594A
Cited
US5313559A
Cited
US5500905A
Cited
US5293456A
Cited
US5493688A
Cited
US5260871A
Cited
US5337371A
Cited
US5251268A
Cited
US5335291A
Cited
US5384863A
Cited
US5325444A
Cited
US5491760A
Cited
US5544257A
Cited
US5245672A
Cited
US5264192A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2000-06-09 | 2000-12-09 | 2001-06-10 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2004-06-09 | 2004-12-09 | 2005-06-10 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2008-06-09 | 2008-12-09 | 2009-06-10 | $7700.00 | Window Closed / Lapsed |