US5276769A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Neural network learning apparatus and method
Assignee: Sharp Corp
•
Filing: 1992-08-06
•
Granted: 1994-01-04
•
Expires: 2012-08-06
Abstract
Abstract A learning apparatus for use in a neural network system which has a plurality of classes representing different meanings. The learning apparatus is provided for learning a number of different patterns, inputted by input vectors, and classified in different classes. The learning apparatus is constructed by a computer and it includes a section for producing a plurality of output vectors representing different classes in response to an input vector, a section for obtaining a first largest output vector of all the output vectors, a section for obtaining a second largest output vector of all the output vectors, and a section for setting predetermined weights to the first and second largest output vectors, respectively, such that the first largest output vector is made larger, and the second largest output vector is made smaller. Furthermore, a section for determining a ratio of the weighted first and second largest output vectors, respectively, is included. If the determined ratio is smaller than a predetermined value, the weighted first and second largest output vectors are further weighted to be made further larger and smaller, respectively.
Inventors
- 👤 Toru Ueda
- 👤 Yasushi Ishizuka
- 👤 Fumio Togawa
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-03 01:05
CPC Classifications
G; G06; G06N; G06N3/00; G06N3/02; G06N3/08; G06F; G06F18/00; G06F18/20; G06F18/24; G06F18/241; G06F18/2413; G06F18/24133; G06F18/24137; G06N3/04; G06N3/0499; G06N3/09
Claims Analysis
Total Claims: 26
Claim 1
Independent Claim
315 words
A learning apparatus for teaching a neural network, including a plurality of input nodes and a plurality of output nodes, each of the plurality of output nodes representing a class with a different meaning, said learning apparatus comprising: initialization means for providing an input learning vector to the plurality of input nodes of said neural network, said neural network applying a weighting vector to the input learning vector to produce an initial output learning vector at the plurality of output nodes; first classifying means including, first selecting means for selecting two of the plurality of output nodes with a first and second largest value, first detecting means for detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs, and weight adjusting means for adjusting the weighting vector if the selected output node with the first largest value does not represent the class to which the input learning vector belongs wherein the adjusted weighting vector is applied to the input learning vector to produce an adjusted output learning vector at the plurality of output nodes, said weight adjusting means adjusting the weighting vector until the first largest value represents the class to which the input vector belongs; and second classifying means including, second selecting means for selecting the two of the plurality of output nodes with the first and second largest values, second detecting means for detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs, ratio calculating means for calculating a ratio of the first largest value to the second largest value if the first largest value represents the class to which the input learning vector belongs, and ratio increasing mean for increasing the ratio of the first largest value to the second largest value if the ratio is within a predetermined range.
Claim 2
Dependent Claim
315 words
A learning apparatus for teaching a neural network, including a plurality of input nodes and a plurality of output nodes, each of the plurality of output nodes representing a class with a different meaning, said learning apparatus comprising: initialization means for providing an input learning vector to the plurality of input nodes of said neural network, said neural network applying a weighting vector to the input learning vector to produce an initial output learning vector at the plurality of output nodes; first classifying means including, first selecting means for selecting two of the plurality of output nodes with a first and second largest value, first detecting means for detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs, and weight adjusting means for adjusting the weighting vector if the selected output node with the first largest value does not represent the class to which the input learning vector belongs wherein the adjusted weighting vector is applied to the input learning vector to produce an adjusted output learning vector at the plurality of output nodes, said weight adjusting means adjusting the weighting vector until the first largest value represents the class to which the input vector belongs; and second classifying means including, second selecting means for selecting the two of the plurality of output nodes with the first and second largest values, second detecting means for detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs, ratio calculating means for calculating a ratio of the first largest value to the second largest value if the first largest value represents the class to which the input learning vector belongs, and ratio increasing mean for increasing the ratio of the first largest value to the second largest value if the ratio is within a predetermined range.
Claim 3
Dependent Claim
36 words
The learning apparatus of claim 1, wherein said initializing means produces the initial output weighting vector according to: ##EQU8## where O jk (t,u)=the initial output vector, I(t)=the input learning vector, and W jk (u)=the weighting vector.
Claim 4
Dependent Claim
73 words
The learning apparatus of claim 1, wherein said weight adjusting means adjusts the weighting vector according to: W.sub.j1k1 =W.sub.j1k1 -K.sub.1 {I-W.sub.j1k1 } and W.sub.j2k2 =W.sub.j2k2 +K.sub.1 {I-W.sub.j1k1 } where W j1k1 =the adjusted weighting vector applied to the selected output mode with the first largest value, W j2k2 =the adjusted weighting vector applied to the selected output mode with the second largest value, I=the input learning vector, and K 1 =is a constant.
Claim 5
Dependent Claim
15 words
The learning apparatus of claim 1, wherein the predetermined range is between 1.0 and 1.5.
Claim 6
Dependent Claim
16 words
The learning apparatus of claim 4, wherein an optimal value in the predetermined range is 1.2.
Claim 7
Dependent Claim
86 words
The learning apparatus of claim 1, wherein said ratio increasing means increases the ratio of the first largest value to the second largest value by adjusting the weighting vector according to: W.sub.j1k1 =W.sub.j1k1 +K.sub.2 {I-W.sub.j1k1 } W.sub.j2k2 =W.sub.j2k2 -K.sub.2 {I-W.sub.j2k2 } where W j1k1 =the adjusted weighting vector applied to the selected output mode with the first largest value, W j2k2 =the adjusted weighting vector applied to the selected output mode with the second largest value, I=the input learning vector, and K 2 =is a constant.
Claim 8
Dependent Claim
185 words
A learning apparatus for teaching a neural network, including a plurality of input nodes and a plurality of output nodes, each of the plurality of output nodes representing a class with a different meaning, said learning apparatus comprising: initialization means for providing an input learning vector to the plurality of input nodes of said neural network, said neural network applying a weighting vector to the input learning vector to produce an initial output learning vector at the plurality of output nodes; and classifying means including, selecting means for selecting two of the plurality of output modes with the first and second largest values, detecting means for detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs, ratio calculating means for calculating a ratio of the first largest value to the second largest value if the first largest value represents the class to which the input learning vector belongs, and ratio increasing means for increasing the ratio of the first largest value to the second largest value if the ratio is within a predetermined range.
Claim 9
Dependent Claim
185 words
A learning apparatus for teaching a neural network, including a plurality of input nodes and a plurality of output nodes, each of the plurality of output nodes representing a class with a different meaning, said learning apparatus comprising: initialization means for providing an input learning vector to the plurality of input nodes of said neural network, said neural network applying a weighting vector to the input learning vector to produce an initial output learning vector at the plurality of output nodes; and classifying means including, selecting means for selecting two of the plurality of output modes with the first and second largest values, detecting means for detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs, ratio calculating means for calculating a ratio of the first largest value to the second largest value if the first largest value represents the class to which the input learning vector belongs, and ratio increasing means for increasing the ratio of the first largest value to the second largest value if the ratio is within a predetermined range.
Claim 10
Dependent Claim
36 words
The learning apparatus of claim 7, wherein said initializing means produces the initial output weighting vector according to: ##EQU9## where O jk (t,u)=the initial output vector, I(t)=the input learning vector, and W jk (u)=the weighting vector.
Claim 11
Dependent Claim
15 words
The learning apparatus of claim 7, wherein the predetermined range is between 1.0 and 1.5.
Claim 12
Dependent Claim
16 words
The learning apparatus of claim 9, wherein an optimal value in the predetermined range is 1.2.
Claim 13
Dependent Claim
94 words
The learning apparatus of claim 7, wherein said ratio increasing means increases the ratio of the first largest value to the second largest value by adjusting the weighting vector according to: W j1k1 =W j1k1 +K 2 {I-W j1k1 } W j2k2 =W j2k2 -K 2 {I-W j2k2 .tbd. where W j1k1 =the adjusting weighting vector applied to the selected output mode with the first largest value, W j2k2 =the adjusted weighting vector applied to the selected output mode with the second largest value, I=the input learning vector, and K 2 =is a constant.
Claim 14
Dependent Claim
284 words
A learning method for teaching a neural network, including a plurality of input nodes and a plurality of output nodes, each of the plurality of output nodes representing a class with a different meaning, said learning method comprising the steps of: (a) providing an input learning vector to the plurality of input nodes of said neural network, said neural network applying a weighting vector to the input learning vector to produce an initial output learning vector at the plurality of output nodes; (b) selecting two of the plurality of output nodes with a first and second largest value; (c) detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs; (d) adjusting the weighting factor if the selected output node with the first largest value does not represent the class to which the input learning vector belongs wherein the adjusted weighting vector is applied to the input learning vector to produce an adjusted output learning vector at the plurality of output nodes, said step (d) adjusting the weighting vector until the first largest value represents the class to which the input vector belongs; (e) selecting the two of the plurality of output nodes with the first and second largest values; (f) detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs; (g) calculating a ratio of the first largest value to the second largest value if the first largest value represents the class to which the input learning vector belongs; and (h) increasing the ratio of the first largest value to the second largest value if the ratio is within a predetermined range.
Claim 15
Dependent Claim
284 words
A learning method for teaching a neural network, including a plurality of input nodes and a plurality of output nodes, each of the plurality of output nodes representing a class with a different meaning, said learning method comprising the steps of: (a) providing an input learning vector to the plurality of input nodes of said neural network, said neural network applying a weighting vector to the input learning vector to produce an initial output learning vector at the plurality of output nodes; (b) selecting two of the plurality of output nodes with a first and second largest value; (c) detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs; (d) adjusting the weighting factor if the selected output node with the first largest value does not represent the class to which the input learning vector belongs wherein the adjusted weighting vector is applied to the input learning vector to produce an adjusted output learning vector at the plurality of output nodes, said step (d) adjusting the weighting vector until the first largest value represents the class to which the input vector belongs; (e) selecting the two of the plurality of output nodes with the first and second largest values; (f) detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs; (g) calculating a ratio of the first largest value to the second largest value if the first largest value represents the class to which the input learning vector belongs; and (h) increasing the ratio of the first largest value to the second largest value if the ratio is within a predetermined range.
Claim 16
Dependent Claim
36 words
The learning method of claim 12, wherein said step (a) produces the initial output weighting vector according to: ##EQU10## where O jk (t,u)=the initial output vector, I(t)=the input learning vector, and W jk (u)=the weighting vector.
Claim 17
Dependent Claim
72 words
The learning method of claim 12, wherein said step (d) adjusts the weighting vector according to: W.sub.j1k1 =W.sub.j1k1 -K.sub.1 {I-W.sub.j1k1 } and W.sub.j2k2 =W.sub.j2k2 +K.sub.1 {I-W.sub.j2k2 } where W j1k1 =the adjusted weighting vector applied to the selected output mode with the first largest value, W j2k2 =the adjusted weighting vector applied to the selected output mode with the second largest value, I=the input learning vector, and K 1 =is a constant.
Claim 18
Dependent Claim
15 words
The learning method of claim 12, wherein the predetermined range is between 1.0 and 1.5.
Claim 19
Dependent Claim
16 words
The learning method of claim 15, wherein an optimal value in the predetermined range is 1.2.
Claim 20
Dependent Claim
85 words
The learning method of claim 12, wherein said step (h) increases the ratio of the first largest value to the second largest value by adjusting the weighting vector according to: W.sub.j1k1 =W.sub.j1k1 +K.sub.2 {I-W.sub.j1k1 } W.sub.j2k2 =W.sub.j2k2 -K.sub.2 {I-W.sub.j2k2 } where W j1k1 =the adjusted weighting vector applied to the selected output mode with the first largest value, W j2k2 =the adjusted weighting vector applied to the selected output mode with the second largest value, I=the input learning vector, and K 2 =is a constant.
Claim 21
Dependent Claim
172 words
A learning method for teaching a neural network, including a plurality of input nodes and a plurality of output nodes, each of the plurality of output nodes representing a class with a different meaning, said learning method comprising the steps of: (a) providing an input learning vector to the plurality of input nodes of said neural network, said neural network applying a weighting vector to the input learning vector to produce an initial output learning vector at the plurality of output nodes; (b) selecting two of the plurality of output nodes with the first and second largest values; (c) detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs; (d) calculating a ratio of the first largest value to the second largest value if the first largest value represents the class to which the input learning vector belongs; and (e) increasing the ratio of the first largest value to the second largest value if the ratio is within a predetermined range.
Claim 22
Dependent Claim
172 words
A learning method for teaching a neural network, including a plurality of input nodes and a plurality of output nodes, each of the plurality of output nodes representing a class with a different meaning, said learning method comprising the steps of: (a) providing an input learning vector to the plurality of input nodes of said neural network, said neural network applying a weighting vector to the input learning vector to produce an initial output learning vector at the plurality of output nodes; (b) selecting two of the plurality of output nodes with the first and second largest values; (c) detecting if the selected output node with the first largest value represents the class to which the input learning vector belongs; (d) calculating a ratio of the first largest value to the second largest value if the first largest value represents the class to which the input learning vector belongs; and (e) increasing the ratio of the first largest value to the second largest value if the ratio is within a predetermined range.
Claim 23
Dependent Claim
36 words
The learning method of claim 18, wherein said step (a) produces the initial output weighting vector according to: ##EQU11## where O jk (t,u)=the initial output vector, I(t)=the input learning vector, and W jk (u)=the weighting vector.
Claim 24
Dependent Claim
15 words
The learning method of claim 18, wherein the predetermined range is between 1.0 and 1.5.
Claim 25
Dependent Claim
16 words
The learning method of claim 18, wherein an optimal value in the predetermined range is 1.2.
Claim 26
Dependent Claim
84 words
The learning method of claim 18, wherein said step (a) increases the ratio of the first largest value to the second largest value by adjusting the weighting vector according to: W.sub.j1k1 =W.sub.j1k1 +K.sub.2 {I-W.sub.j1k1 } W.sub.j2k2 =W.sub.j2k2 -K.sub.2 {I-W.sub.j2k2)} where W j1k1 =the adjusted weighting vector applied to the selected output mode with the first largest value, W j2k2 =the adjusted weighting vector applied to the selected output mode with the second largest value, I=the input learning vector, and K 2 =is a constant.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-01-03 | 1997-07-05 | 1998-01-04 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-01-03 | 2001-07-05 | 2002-01-04 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-01-03 | 2005-07-05 | 2006-01-04 | $7700.00 | Window Closed / Lapsed |