US5359699A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for using a feed forward neural network to perform classification with highly biased data
Assignee: General Electric Co
•
Filing: 1991-12-02
•
Granted: 1994-10-25
•
Expires: 2011-12-02
Abstract
Abstract An artificial neural network detects points in feature space outside of a boundary determined by a set of sample data. The network is trained using pseudo data which compensates for the lack of original data representing "abnormal" or novel combinations of features. The training process is done iteratively using a net bias parameter to close the boundary around the sample data. When the neural net stabilizes, the training process is complete. Pseudo data is chosen using several disclosed methods.
Inventors
- 👤 David W. Tong
- 👤 Paul A. Delano
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-26 16:07
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/08; G06F; G06F18/00; G06F18/20; G06F18/21; G06F18/214; G06N3/04; G06N3/0499; G06N3/09
Claims Analysis
Total Claims: 12
Claim 1
Independent Claim
213 words
A method for using an artificial neural network comprising a plurality of weighted interconnected processing elements forming an input layer, an output layer, and a hidden layer connecting the input layer and the output layer, for performing classification of sensor-based data provided to said network wherein the classes to be used include and inside class consisting of one or more classes for which representative sensor-based data is available and an outside class representing an abnormal or novel class for which representative sensor-based data is unavailable or scarce, said method comprising the steps of: gathering inside data representative of said inside class; generating pseudo data representative of said outside class; inputting said inside data and said pseudo data to said artificial neural network; storing said inputted inside data and said pseudo data in said artificial neural network; training said artificial neural network to reduce the level of classification error output using said inside data and said pseudo data, said training comprising the step of setting a bias parameter for biasing an output term for identifying said inside data; repeating said generating, inputting, storing, and training steps until an acceptable class boundary is formed around said inside data by said artificial neural network; and classifying the sensor-based data in accordance with the accepted class boundary.
Claim 2
Independent Claim
213 words
A method for using an artificial neural network comprising a plurality of weighted interconnected processing elements forming an input layer, an output layer, and a hidden layer connecting the input layer and the output layer, for performing classification of sensor-based data provided to said network wherein the classes to be used include and inside class consisting of one or more classes for which representative sensor-based data is available and an outside class representing an abnormal or novel class for which representative sensor-based data is unavailable or scarce, said method comprising the steps of: gathering inside data representative of said inside class; generating pseudo data representative of said outside class; inputting said inside data and said pseudo data to said artificial neural network; storing said inputted inside data and said pseudo data in said artificial neural network; training said artificial neural network to reduce the level of classification error output using said inside data and said pseudo data, said training comprising the step of setting a bias parameter for biasing an output term for identifying said inside data; repeating said generating, inputting, storing, and training steps until an acceptable class boundary is formed around said inside data by said artificial neural network; and classifying the sensor-based data in accordance with the accepted class boundary.
Claim 3
Dependent Claim
29 words
The method of claim 1 wherein said biasing is adjusted during said training as a function of the accuracy of said neural network in classifying said inside data correctly.
Claim 4
Dependent Claim
25 words
The method of claim 1 wherein said pseudo data is generated randomly within a bounding hypercube large enough to contain all of said inside data.
Claim 5
Dependent Claim
33 words
The method of claim 3 wherein said pseudo data includes pseudo data from previous training iterations, wherein said previously generated pseudo data is close to the boundary as determined by said neural network.
Claim 6
Dependent Claim
61 words
The method of claim 1 wherein said pseudo data is initially generated randomly on a bounding hypercube surface, said hypercube bounding said inside data and wherein said pseudo data is thereafter generated after each said repeating step within said bounding hypercube and selected from those of said pseudo data points which are not classified as inside data by said neural network.
Claim 7
Dependent Claim
23 words
The method of claim 1 wherein said pseudo data is generated on fixed regular matrix points within a hypercube bounding said inside data.
Claim 8
Dependent Claim
14 words
The method of claim 1 wherein said training is performed using backpropagation of errors.
Claim 9
Dependent Claim
15 words
The method of claim 1 wherein said training is performed using a gradient descent method.
Claim 10
Dependent Claim
15 words
The method of claim 1 wherein said training is performed using a conjugate gradient method.
Claim 11
Independent Claim
217 words
A method for using an artificial neural network comprising a plurality of weighted interconnected processing elements forming an input layer, an output layer, and a hidden layer connecting the input layer and the output layer, for performing classification of sensor-based data provided to said network wherein the classes to be used include a plurality of inside classes for which representative sensor-based data is available and an outside class representing an abnormal or noel class for which representative sensor-based data is unavailable or scarce, said method comprising the steps of: gathering inside data representative of said plurality of inside classes; generating pseudo data representative of said outside class; inputting said inside data and said pseudo data to said artificial neural network; storing said inputted inside data and said pseudo data in said artificial neural network; training said neural network to reduce the level of classification error output using said inside data and said pseudo data, said training comprising the step of setting a bias parameter for biasing an output term for identifying said inside data; repeating said generating, inputting, storing, and training steps until acceptable respective class boundaries are formed around said inside data representative of said plurality of inside classes by said artificial neural network; and classifying the sensor-based data in accordance with the accepted class boundary.
Claim 12
Independent Claim
217 words
A method for using an artificial neural network comprising a plurality of weighted interconnected processing elements forming an input layer, an output layer, and a hidden layer connecting the input layer and the output layer, for performing classification of sensor-based data provided to said network wherein the classes to be used include a plurality of inside classes for which representative sensor-based data is available and an outside class representing an abnormal or noel class for which representative sensor-based data is unavailable or scarce, said method comprising the steps of: gathering inside data representative of said plurality of inside classes; generating pseudo data representative of said outside class; inputting said inside data and said pseudo data to said artificial neural network; storing said inputted inside data and said pseudo data in said artificial neural network; training said neural network to reduce the level of classification error output using said inside data and said pseudo data, said training comprising the step of setting a bias parameter for biasing an output term for identifying said inside data; repeating said generating, inputting, storing, and training steps until acceptable respective class boundaries are formed around said inside data representative of said plurality of inside classes by said artificial neural network; and classifying the sensor-based data in accordance with the accepted class boundary.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-10-24 | 1998-04-25 | 1998-10-25 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-10-24 | 2002-04-25 | 2002-10-25 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-10-24 | 2006-04-25 | 2006-10-25 | $7700.00 | Window Closed / Lapsed |