US5235673A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Enhanced neural network shell for application programs
Assignee: International Business Machines Corp
•
Filing: 1991-04-18
•
Granted: 1993-08-10
•
Expires: 2011-04-18
Abstract
Abstract An enhanced neural network shell for application programs is disclosed. The user is prompted to enter in non-technical information about the specific problem type that the user wants solved by a neural network. The user also is prompted to indicate the input data usage information to the neural network. Based on this information, the neural network shell creates a neural network data structure by automatically selecting an appropriate neural network model and automatically generating an appropriate number of inputs, outputs, and/or other model-specific parameters for the selected neural network model. The user is no longer required to have expertise in neural network technology to create a neural network data structure.
Inventors
- 👤 Shawn M. Austvold
- 👤 Joseph P. Bigus
- 👤 Jonathan D. Henckel
- 👤 Paul A. Hospers
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-31 09:54
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/10; G06N3/105
Claims Analysis
Total Claims: 40
Claim 1
Independent Claim
90 words
A method of creating a neural network data structure for a neural network, comprising the machine executed steps of: prompting a user for a problem type; prompting said user for an input data file, said input data file having an input data format; selecting a neural network model based on said problem type and said input data format; prompting said user for input data usage information; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 2
Independent Claim
90 words
A method of creating a neural network data structure for a neural network, comprising the machine executed steps of: prompting a user for a problem type; prompting said user for an input data file, said input data file having an input data format; selecting a neural network model based on said problem type and said input data format; prompting said user for input data usage information; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 3
Independent Claim
92 words
A method of creating a neural network data structure for a neural network, comprising the machine executed steps of: prompting a user for a problem type; prompting said user for an input data file, said input data file having an input data file size; selecting a neural network model based on said problem type and said input data file size; prompting said user for input data usage information; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 4
Independent Claim
92 words
A method of creating a neural network data structure for a neural network, comprising the machine executed steps of: prompting a user for a problem type; prompting said user for an input data file, said input data file having an input data file size; selecting a neural network model based on said problem type and said input data file size; prompting said user for input data usage information; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 5
Independent Claim
101 words
A method of creating a neural network data structure for a neural network, comprising the machine executed steps of: prompting a user for a problem type; prompting said user for an input data file, said input data file having an input data format and an input data file size; selecting a neural network model based on said problem type, said input data format, and said input data file size; prompting said user for input data usage information; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 6
Independent Claim
101 words
A method of creating a neural network data structure for a neural network, comprising the machine executed steps of: prompting a user for a problem type; prompting said user for an input data file, said input data file having an input data format and an input data file size; selecting a neural network model based on said problem type, said input data format, and said input data file size; prompting said user for input data usage information; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 7
Independent Claim
68 words
A method of creating a neural network data structure for a neural network, comprising the machine executed steps of: prompting a user for a problem type; selecting a neural network model based on said problem type; prompting said user for input data usage information; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 8
Independent Claim
68 words
A method of creating a neural network data structure for a neural network, comprising the machine executed steps of: prompting a user for a problem type; selecting a neural network model based on said problem type; prompting said user for input data usage information; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 9
Dependent Claim
103 words
A computer system for creating a neural network data structure for a neural network in a computer system, said apparatus comprising: means for prompting a user for a problem type; means for prompting said user for an input data file, said input data file having an input data format; means for selecting a neural network model based on said problem type and said input data format; and means for prompting said user for input data usage information; and means for creating said neural network data structure for said neural network model selected by said selecting means based on said input data usage information.
Claim 10
Dependent Claim
103 words
A computer system for creating a neural network data structure for a neural network in a computer system, said apparatus comprising: means for prompting a user for a problem type; means for prompting said user for an input data file, said input data file having an input data format; means for selecting a neural network model based on said problem type and said input data format; and means for prompting said user for input data usage information; and means for creating said neural network data structure for said neural network model selected by said selecting means based on said input data usage information.
Claim 11
Dependent Claim
98 words
A computer system for creating a neural network data structure for a neural network, comprising: means for prompting a user for a problem type; means for prompting said user for an input data file, said input data file having an input data file sizes; means for selecting a neural network model based on said problem type and said input data file size; means for prompting said user for input data usage information; and means for creating said neural network data structure for said neural network model selected by said selecting means based on said input data usage information.
Claim 12
Dependent Claim
98 words
A computer system for creating a neural network data structure for a neural network, comprising: means for prompting a user for a problem type; means for prompting said user for an input data file, said input data file having an input data file sizes; means for selecting a neural network model based on said problem type and said input data file size; means for prompting said user for input data usage information; and means for creating said neural network data structure for said neural network model selected by said selecting means based on said input data usage information.
Claim 13
Dependent Claim
107 words
A computer system for creating a neural network data structure for a neural network, comprising: means for prompting a user for a problem type; means for prompting said user for an input data file, said input data file having an input data format and an input data file size; means for selecting a neural network model based on said problem type, said input data format, and said input data file size; means for prompting said user for input data usage information; and means for creating said neural network data structure for said neural network model selected by said selecting means based on said input data usage information.
Claim 14
Dependent Claim
107 words
A computer system for creating a neural network data structure for a neural network, comprising: means for prompting a user for a problem type; means for prompting said user for an input data file, said input data file having an input data format and an input data file size; means for selecting a neural network model based on said problem type, said input data format, and said input data file size; means for prompting said user for input data usage information; and means for creating said neural network data structure for said neural network model selected by said selecting means based on said input data usage information.
Claim 15
Dependent Claim
72 words
A computer system for creating a neural network data structure for a neural network, comprising: means for prompting a user for a problem type; means for selecting a neural network model based on said problem type; means for prompting said user for input data usage information; and means for creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 16
Dependent Claim
72 words
A computer system for creating a neural network data structure for a neural network, comprising: means for prompting a user for a problem type; means for selecting a neural network model based on said problem type; means for prompting said user for input data usage information; and means for creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 17
Independent Claim
103 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a closed path problem type; selecting a self organized routing neural network model; prompting said user for input data usage information, said input data usage information containing a user specified maximum number of destinations; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 18
Independent Claim
103 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a closed path problem type; selecting a self organized routing neural network model; prompting said user for input data usage information, said input data usage information containing a user specified maximum number of destinations; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 19
Independent Claim
137 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a classification problem type; prompting said user for an input data file, said input data file having an input data file size; determining the input data size is smaller than a predetermined threshold value; selecting a back propagation neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of outputs; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 20
Independent Claim
137 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a classification problem type; prompting said user for an input data file, said input data file having an input data file size; determining the input data size is smaller than a predetermined threshold value; selecting a back propagation neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of outputs; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 21
Dependent Claim
22 words
The method of claim 10, further comprising the step of: translating said data input file to create a translated data input file.
Claim 22
Dependent Claim
42 words
The method of claim 11, wherein said creating step further comprises the step of: initializing a number of inputs parameter in said back propagation neural network model to be equal to the number of inputs present in said translated input data file.
Claim 23
Dependent Claim
61 words
The method of claim 12, wherein said creating step further comprises the step of: initializing a number of first hidden inputs parameter in said back propagation neural network model to be equal to the sum of the number of inputs present in said translated data input file and the number of outputs present in said translated data input file plus one.
Claim 24
Dependent Claim
32 words
The method of claim 13, wherein said creating step further comprises the step of: initializing a number of second hidden inputs parameter in said back propagation neural network model to be zero.
Claim 25
Dependent Claim
32 words
The method of claim 14, wherein said creating step further comprises the step of: initializing a number of third hidden inputs parameter in said back propagation neural network model to be zero.
Claim 26
Dependent Claim
41 words
The method of claim 15, wherein said creating step further comprises the step of: initializing a number of outputs parameter in said back propagation neural network model to equal to the number of outputs present in said translated data input file.
Claim 27
Independent Claim
137 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a classification problem type; prompting said user for an input data file, said input data file having an input data file size; determining the input data file size exceeds a predetermined threshold value; selecting a learning vector quantization neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of outputs; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 28
Independent Claim
137 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a classification problem type; prompting said user for an input data file, said input data file having an input data file size; determining the input data file size exceeds a predetermined threshold value; selecting a learning vector quantization neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of outputs; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 29
Independent Claim
113 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a time series problem type; selecting a back propagation neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs, a user specified number of outputs, and a user specified window size; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 30
Independent Claim
113 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a time series problem type; selecting a back propagation neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs, a user specified number of outputs, and a user specified window size; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 31
Independent Claim
113 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a scheduling problem type; selecting a constraint satisfaction neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of tasks, a user specified number of resources, and a user specified number of constraints; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 32
Independent Claim
113 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a scheduling problem type; selecting a constraint satisfaction neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of tasks, a user specified number of resources, and a user specified number of constraints; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 33
Independent Claim
114 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a resource allocation problem type; selecting a constraint satisfaction neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of tasks, a user specified number of resources, and a user specified number of constraints; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 34
Independent Claim
114 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a resource allocation problem type; selecting a constraint satisfaction neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of tasks, a user specified number of resources, and a user specified number of constraints; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 35
Independent Claim
115 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a data reconstruction problem type; determining the input data is real valued; selecting a back propagation neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of outputs; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 36
Independent Claim
115 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a data reconstruction problem type; determining the input data is real valued; selecting a back propagation neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of outputs; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 37
Independent Claim
135 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a cluster analysis problem type; prompting said user for an input data file, said input data file having an input data format; determining the input data format is real valued; selecting a self organizing feature map neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of clusters; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 38
Independent Claim
135 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a cluster analysis problem type; prompting said user for an input data file, said input data file having an input data format; determining the input data format is real valued; selecting a self organizing feature map neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of clusters; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 39
Independent Claim
132 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a cluster analysis problem type; prompting said user for an input data file, said input data file having an input data format; determining the input data format is binary; selecting an adaptive resonance neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of outputs; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
Claim 40
Independent Claim
132 words
A method of selecting a neural network model for a neural network, comprising the machine executed steps of: prompting a user for a problem type; receiving an indication from said user that said problem type is a cluster analysis problem type; prompting said user for an input data file, said input data file having an input data format; determining the input data format is binary; selecting an adaptive resonance neural network model; prompting said user for input data usage information, said input data usage information containing a user specified number of inputs and a user specified number of outputs; receiving said input data usage information from said user; and creating said neural network data structure for said neural network model selected by said selecting step based on said input data usage information.
References Cited (Backward Citations)
US5142665A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1996-08-09 | 1997-02-08 | 1997-08-10 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2000-08-09 | 2001-02-08 | 2001-08-10 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2004-08-09 | 2005-02-08 | 2005-08-10 | $7700.00 | Window Closed / Lapsed |