US5664067A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for training a neural network
Assignee: United Parcel Service of America Inc
•
Filing: 1995-01-11
•
Granted: 1997-09-02
•
Expires: 2015-01-11
Abstract
Abstract A plurality of training inputs are selected, wherein each training input corresponds to a first possible output. The quality of each of the plurality of training inputs is characterized. A first training input is selected from the training inputs, where the first training input is of higher quality than a second training input of the training inputs. The neural network is trained with the higher-quality first training input prior to training with the second training input. A neuron may be added to the neural network in accordance with the first training input, wherein the neuron is associated with the first possible output.
Inventors
- 👤 Michael C. Moed
- 👤 Chih-Ping Lee
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-02 22:42
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: 29
Claim 1
Independent Claim
77 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs such that the neural network is trained with higher quality training inputs of each set before being trained with lower quality training inputs of the set, wherein each set of training inputs corresponds to one output; and (b) sequentially training the neural network using said organized sets of training inputs.
Claim 2
Independent Claim
77 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs such that the neural network is trained with higher quality training inputs of each set before being trained with lower quality training inputs of the set, wherein each set of training inputs corresponds to one output; and (b) sequentially training the neural network using said organized sets of training inputs.
Claim 3
Dependent Claim
39 words
The method of claim 1, wherein step (b) comprises the step of training the neural network with the higher quality training inputs of all sets before training the neural network with the lower quality training inputs of any set.
Claim 4
Dependent Claim
39 words
The method of claim 1, wherein step (b) comprises the step of training the neural network with all of the training inputs of each set before training the neural network with any of the training inputs of another set.
Claim 5
Dependent Claim
44 words
The method of claim 1, wherein: each training input comprises one or more pixels; and step (a) comprises the step of basing the quality of the training inputs on a number of pixels that differ between each training input and a corresponding nominal input.
Claim 6
Dependent Claim
23 words
The method of claim 1, wherein step (a) comprises the step of basing the quality of the training inputs on a feature measure.
Claim 7
Dependent Claim
19 words
The method of claim 5, wherein the feature measure is a Grid feature measure or a Hadamard feature measure.
Claim 8
Dependent Claim
35 words
The method of claim 1, wherein step (b) comprises the step of training the neural network with nominal training inputs of each set before training the neural network with degraded training inputs of the set.
Claim 9
Dependent Claim
35 words
The method of claim 7, wherein step (b) further comprises the step of training the neural network with the less highly degraded training inputs before training the neural network with more highly degraded training inputs.
Claim 10
Dependent Claim
13 words
The method of claim 1, wherein the training inputs are representative of characters.
Claim 11
Dependent Claim
16 words
The method of claim 1, wherein the neural network accurately classifies each of the training inputs.
Claim 12
Independent Claim
78 words
An apparatus for training a neural network, comprising: (a) means for organizing one or more sets of training inputs based on quality of the training inputs such that the neural network is trained with higher quality training inputs of each set before being trained with lower quality training inputs of the set, wherein each set of training inputs corresponds to one output; and (b) means for sequentially training the neural network using said organized sets of training inputs.
Claim 13
Independent Claim
78 words
An apparatus for training a neural network, comprising: (a) means for organizing one or more sets of training inputs based on quality of the training inputs such that the neural network is trained with higher quality training inputs of each set before being trained with lower quality training inputs of the set, wherein each set of training inputs corresponds to one output; and (b) means for sequentially training the neural network using said organized sets of training inputs.
Claim 14
Dependent Claim
41 words
The apparatus of claim 11, wherein said means for sequentially training the neural network trains the neural network with the higher quality training inputs of all sets before training the neural network with the lower quality training inputs of any set.
Claim 15
Dependent Claim
41 words
The apparatus of claim 11, wherein said means for sequentially training the neural network trains the neural network with all of the training inputs of each set before training the neural network with any of the training inputs of another set.
Claim 16
Dependent Claim
42 words
The apparatus of claim 11, wherein: each training input comprises one or more pixels; and said means for organizing bases the quality of the training inputs on a number of pixels that differ between each training input and a corresponding nominal input.
Claim 17
Dependent Claim
25 words
The apparatus of claim 11, wherein said means for organizing comprises the step of basing the quality of the training inputs on a feature measure.
Claim 18
Independent Claim
84 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein: each set of training inputs corresponds to one output; each training input comprises one or more pixels; and the quality of the training inputs is based on a number of pixels that differ between each training input and a corresponding nominal input; and (b) sequentially training the neural network using said organized sets of training inputs.
Claim 19
Independent Claim
84 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein: each set of training inputs corresponds to one output; each training input comprises one or more pixels; and the quality of the training inputs is based on a number of pixels that differ between each training input and a corresponding nominal input; and (b) sequentially training the neural network using said organized sets of training inputs.
Claim 20
Independent Claim
64 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein each set of training inputs corresponds to one output and the quality of the training inputs is based on a feature measure; and (b) sequentially training the neural network using said organized sets of training inputs.
Claim 21
Independent Claim
64 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein each set of training inputs corresponds to one output and the quality of the training inputs is based on a feature measure; and (b) sequentially training the neural network using said organized sets of training inputs.
Claim 22
Dependent Claim
19 words
The method of claim 17, wherein the feature measure is a Grid feature measure or a Hadamard feature measure.
Claim 23
Independent Claim
76 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein each set of training inputs corresponds to one output; and (b) sequentially training the neural network using said organized sets of training inputs, wherein the neural network is trained with nominal training inputs of each set before training the neural network with degraded training inputs of the set.
Claim 24
Independent Claim
76 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein each set of training inputs corresponds to one output; and (b) sequentially training the neural network using said organized sets of training inputs, wherein the neural network is trained with nominal training inputs of each set before training the neural network with degraded training inputs of the set.
Claim 25
Dependent Claim
35 words
The method of claim 19, wherein step (b) further comprises the step of training the neural network with the less highly degraded training inputs before training the neural network with more highly degraded training inputs.
Claim 26
Independent Claim
59 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein each set of training inputs corresponds to one output and the training inputs are representative of characters; and (b) sequentially training the neural network using said organized sets of training inputs.
Claim 27
Independent Claim
59 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein each set of training inputs corresponds to one output and the training inputs are representative of characters; and (b) sequentially training the neural network using said organized sets of training inputs.
Claim 28
Independent Claim
62 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein each set of training inputs corresponds to one output; and (b) sequentially training the neural network using said organized sets of training inputs, wherein the neural network accurately classifies each of the training inputs.
Claim 29
Independent Claim
62 words
A method for training a neural network, comprising the steps of: (a) organizing one or more sets of training inputs based on quality of the training inputs, wherein each set of training inputs corresponds to one output; and (b) sequentially training the neural network using said organized sets of training inputs, wherein the neural network accurately classifies each of the training inputs.
References Cited (Backward Citations)
US3701095A
Cited
US3950733A
Cited
US4044243A
Cited
US4326259A
Cited
US4599693A
Cited
US5054093A
Cited
JPS62133589A
Cited
JPH0233687A
Cited
US5046020A
Cited
US5010512A
Cited
US5297237A
Cited
US4954963A
Cited
US5293454A
Cited
US5119438A
Cited
US5033006A
Cited
JPH02238588A
Cited
JPH02242392A
Cited
US5140530A
Cited
JPH02300876A
Cited
US5060278A
Cited
US5086479A
Cited
US5150323A
Cited
US5426745A
Cited
US5339818A
Cited
US5067164A
Cited
US5311601A
Cited
US5218646A
Cited
US5220618A
Cited
US5299284A
Cited
US5175796A
Cited
US5245697A
Cited
US5058180A
Cited
US5181171A
Cited
US5265192A
Cited
US5214744A
Cited
US5247584A
Cited
US5214715A
Cited
US5239594A
Cited
US5479575A
Cited
US5313559A
Cited
US5500905A
Cited
US5293456A
Cited
US5493688A
Cited
US5260871A
Cited
US5337371A
Cited
US5251268A
Cited
US5335291A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2000-09-01 | 2001-03-03 | 2001-09-02 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2004-09-01 | 2005-03-03 | 2005-09-02 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2008-09-01 | 2009-03-03 | 2009-09-02 | $7700.00 | Window Closed / Lapsed |