Method and apparatus for input classification using non-spherical neurons

Claim 2

A classification method for classifying an input into one of a plurality of possible outputs, comprising the steps of: (a) comparing information representative of said input to a neuron, wherein said neuron comprises a boundary defined by two or more neuron axes, wherein the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; and (b) selecting one of said possible outputs as corresponding to said input in accordance with the comparison of step (a), wherein: step (a) comprises the step of comparing information representative of said input to a plurality of neurons; each neuron of said plurality of neurons comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said information representative of said input comprises a feature vector; step (a) further comprises the step of selecting each neuron that encompasses said feature vector; and step (b) further comprises the steps of: (i) determining a first number that is a function of the number of said selected neurons that are associated with a first possible output of said plurality of possible outputs; (ii) de. termining a second number that is a function of the number of said selected neurons that are associated with a second possible output of said plurality of possible outputs; and (iii) if said first number is greater than said second number then determining that said input does not correspond to said second possible output, else if said second number is greater than said first number then determining that said input does not correspond to said first possible output.

Claim 3

The classification method of claim 1, wherein said input is representative of a character.

Claim 4

The classification method of claim 1, wherein said information representative of said input comprises a feature vector.

Claim 5

The classification method of claim 3, wherein said feature Vector comprises a feature element, wherein said feature element is a Grid feature element or a Hadamard feature element.

Claim 6

The classification method of claim 3, wherein step (a) comprises the step of determining whether said neuron encompasses said feature vector.

Claim 7

The classification method of claim 3, wherein step (a) comprises the step of determining a distance measure from said feature vector to said neuron.

Claim 8

The classification method of claim 1, wherein said neuron is a hyper-ellipse or a hyper-rectangle in k-dimensional feature space, where k is greater than or equal to two.

Claim 9

The classification method of claim 1, wherein said neuron is in a feature space comprising two or more feature-space axes, wherein at least one of said neuron axes is parallel to one of said feature-space axes.

Claim 10

The classification method of claim 1, wherein said neuron is in a feature space comprising two or more feature-space axes, wherein at least one of said neuron axes is parallel to none of said feature-space axes.

Claim 11

The classification method of claim 1, wherein said first number is equal to the number of said selected neurons that are associated with said first possible output, and said second number that is equal to the number of said selected neurons that are associated with said second possible output.

Claim 12

A training method for creating a new neuron in a feature space having at least one existing neuron, comprising the steps of: (a) generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; (b) determining whether any existing neuron corresponding to said training input encompasses said feature vector; and (c) creating said new neuron in accordance with the determination of step (b), wherein: said new neuron comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said feature space comprises an existing feature vector; step (c) comprises the steps of: (i) creating a temporary neuron comprising a boundary defined by two or more tempQrary neuron axes; and (ii) if said temporary neuron encompasses said existing feature vector and said existing feature vector does not correspond to said training input then spatially adjusting said temporary neuron to create said new neuron; and step (c)(ii) comprises the steps of: (1) selecting at least one of said temporary neuron axes; (2) calculating the distances along each of said selected temporary neuron axes from the center of said temporary neuron to said existing feature vector; and (3) reducing said selected temporary neuron axes by amounts proportional to said distances and the lengths of said selected temporary neuron axes to create said new neuron.

Claim 13

A training method for creating a new neuron in a feature space having at least one existing neuron, comprising the steps of: (a) generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; (b) determining whether any existing neuron corresponding to said training input encompasses said feature vector; and (c) creating said new neuron in accordance with the determination of step (b), wherein: said new neuron comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said feature space comprises an existing feature vector; step (c) comprises the steps of: (i) creating a temporary neuron comprising a boundary defined by two or more tempQrary neuron axes; and (ii) if said temporary neuron encompasses said existing feature vector and said existing feature vector does not correspond to said training input then spatially adjusting said temporary neuron to create said new neuron; and step (c)(ii) comprises the steps of: (1) selecting at least one of said temporary neuron axes; (2) calculating the distances along each of said selected temporary neuron axes from the center of said temporary neuron to said existing feature vector; and (3) reducing said selected temporary neuron axes by amounts proportional to said distances and the lengths of said selected temporary neuron axes to create said new neuron.

Claim 14

The training method of claim 11, wherein said training input is representative of a character.

Claim 15

The training method of claim 11, wherein said information representative of said input comprises a feature vector.

Claim 16

The training method of claim 13, wherein said feature vector comprises a feature element, wherein said feature element is a Grid feature element or a Hadamard feature element.

Claim 17

The training method of claim 11, wherein said new neuron is a hyper-ellipse or a hyper-rectangle in k-dimensional feature space, where k is greater than or equal to two.

Claim 18

The training method of claim 11, wherein said feature space comprises two or more feature-space axes, and wherein at least one of said neuron axes is parallel to one of said feature-space axes.

Claim 19

The training method of claim 11, wherein said feature space comprises two or more feature-space axes, and wherein at least one of said neuron axes is parallel to none of said feature-space axes.

Claim 20

The training method of claim 11, wherein step (c)(ii)(1) comprises the step of selecting all of said temporary neuron axes.

Claim 21

The training method of claim 11, wherein step (c)(ii) comprises the steps of: (1) selecting only one of said temporary neuron axes; (2) calculating a distance in accordance with said selected temporary neuron axis and said existing feature vector; and (3) reducing said selected temporary neuron axis by said distance to create said new neuron.

Claim 22

A training method for adjusting a neuron, comprising the steps of: (a) generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; (b) determining whether said neuron encompasses said feature vector and whether said neuron does not correspond to said training input; and (c) spatially adjusting said neuron in accordance with the determination of step (b), wherein: said adjusted neuron comprises a boundary defined by two or more adjusted neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said neuron is in a feature space comprising an existing feature vector; said neuron comprises a boundary defined by two or more neuron axes; and step (c) further comprises the steps of: (i) selecting at least one of said neuron axes; (ii) calculating the distances along each of said selected neuron axes from the center of said neuron to said existing feature vector; and (iii) reducing said selected neuron axes by amounts proportional to said distances and the lengths of said selected neuron axes to create said adjusted neuron.

Claim 23

A training method for adjusting a neuron, comprising the steps of: (a) generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; (b) determining whether said neuron encompasses said feature vector and whether said neuron does not correspond to said training input; and (c) spatially adjusting said neuron in accordance with the determination of step (b), wherein: said adjusted neuron comprises a boundary defined by two or more adjusted neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said neuron is in a feature space comprising an existing feature vector; said neuron comprises a boundary defined by two or more neuron axes; and step (c) further comprises the steps of: (i) selecting at least one of said neuron axes; (ii) calculating the distances along each of said selected neuron axes from the center of said neuron to said existing feature vector; and (iii) reducing said selected neuron axes by amounts proportional to said distances and the lengths of said selected neuron axes to create said adjusted neuron.

Claim 24

The training method of claim 20, wherein said training input is representative of a character.

Claim 25

The training method of claim 20, wherein said information representative of said input comprises a feature vector.

Claim 26

The training method of claim 22, wherein said feature vector comprises a feature element, wherein said feature element is a Grid feature element or a Hadamard feature element.

Claim 27

The training method of claim 20, wherein said neuron is a hyper-ellipse or a hyper-rectangle in k-dimensional feature space, where k is greater than or equal to two.

Claim 28

The training method of claim 20, wherein said feature space comprises two or more feature-space axes, and wherein at least one of said adjusted neuron axes is parallel to one of said feature-space axes.

Claim 29

The training method of claim 20, wherein said feature space comprises two or more feature-space axes, and wherein at least one of said adjusted neuron axes is parallel to none of said feature-space axes.

Claim 30

The training method of claim 20, wherein step (c)(i) comprises the step of selecting all of said neuron axes.

Claim 31

The training method of claim 20, wherein step (c) comprises the steps of: (i) selecting only one of said neuron axes; and (ii) calculating a distance in accordance with said selected neuron axis and said existing feature vector; and (iii) reducing said selected neuron axis by said distance to create said adjusted neuron.

Claim 32

A classification apparatus for classifying an input into one of a plurality of possible outputs, comprising: comparing means for comparing information representative of said input to a neuron, wherein said neuron comprises a boundary defined by two or more neuron axes, wherein the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; and selecting means for selecting one of said possible outputs as corresponding to said input in accordance with the comparison by said comparing means; wherein: said comparing means compares information representative of said input to a plurality of neurons; each neuron of said plurality of neurons comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said information representative of said input comprises a feature vector; said comparing means selects each neuron that encompasses said feature vector; said selecting means determines a first number that is a function of the number of said selected neurons that are associated with a first possible output of said plurality of possible outputs; said selecting means determines a second number that is a function of the number of said selected neurons that are associated with a second possible output of said plurality of possible outputs; if said first number is greater than said second number, then said selecting means determines that said input does not correspond to said second possible output, else if said second number is greater than said first number, then said selecting means determines that said input does not correspond to said first possible output.

Claim 33

A classification apparatus for classifying an input into one of a plurality of possible outputs, comprising: comparing means for comparing information representative of said input to a neuron, wherein said neuron comprises a boundary defined by two or more neuron axes, wherein the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; and selecting means for selecting one of said possible outputs as corresponding to said input in accordance with the comparison by said comparing means; wherein: said comparing means compares information representative of said input to a plurality of neurons; each neuron of said plurality of neurons comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said information representative of said input comprises a feature vector; said comparing means selects each neuron that encompasses said feature vector; said selecting means determines a first number that is a function of the number of said selected neurons that are associated with a first possible output of said plurality of possible outputs; said selecting means determines a second number that is a function of the number of said selected neurons that are associated with a second possible output of said plurality of possible outputs; if said first number is greater than said second number, then said selecting means determines that said input does not correspond to said second possible output, else if said second number is greater than said first number, then said selecting means determines that said input does not correspond to said first possible output.

Claim 34

The classification apparatus of claim 29, wherein said input is representative of a character.

Claim 35

The classification apparatus of claim 29, wherein said information representative of said input comprises a feature vector.

Claim 36

The classification apparatus of claim 31, wherein said feature vector comprises a feature element, wherein said feature element is a Grid feature element or a Hadamard feature element.

Claim 37

The classification apparatus of claim 31, wherein said comparing means determines whether said neuron encompasses said feature vector.

Claim 38

The classification apparatus of claim 31, wherein said comparing means determines a distance measure from said feature vector to said neuron.

Claim 39

The classification apparatus of claim 29, wherein said neuron is a hyper-ellipse or a hyper-rectangle in k-dimensional feature space, where k is greater than or equal to two.

Claim 40

The classification apparatus of claim 29, wherein said neuron is in a feature space comprising two or more feature-space axes, wherein at least one of said neuron axes is parallel to one of said feature-space axes.

Claim 41

The classification apparatus of claim 29, wherein said neuron is in a feature space comprising two or more feature-space axes, wherein at least one of said neuron axes is parallel to none of said feature-space axes.

Claim 42

The classification apparatus of claim 29, wherein said first number is equal to the number of said selected neurons that are associated with said first possible output, and said second number that is equal to the number of said selected neurons that are associated with said second possible output.

Claim 43

A training apparatus for creating a new neuron in a feature space having at least one existing neuron, comprising: generating means for generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; and creating means for creating said new neuron, if no existing neuron corresponding to said training input encompasses said feature vector, wherein: said new neuron comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said feature space comprises an existing feature vector; said creating means creates a temporary. neuron comprising a boundary defined by two or more temporary neuron axes; if said temporary neuron encompasses said existing feature vector and said existing feature vector does not correspond to said training input, then said creating means spatially adjusts said temporary neuron to create said new neuron; said creating means selects at least one of said temporary neuron axes; said creating means calculates the distances along each of said selected temporary neuron axes from the center of said temporary neuron to said existing feature vector; and said creating means reduces said selected temporary neuron axes by amounts proportional to said distances and the lengths of said selected temporary neuron axes to create said new neuron.

Claim 44

A training apparatus for creating a new neuron in a feature space having at least one existing neuron, comprising: generating means for generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; and creating means for creating said new neuron, if no existing neuron corresponding to said training input encompasses said feature vector, wherein: said new neuron comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said feature space comprises an existing feature vector; said creating means creates a temporary. neuron comprising a boundary defined by two or more temporary neuron axes; if said temporary neuron encompasses said existing feature vector and said existing feature vector does not correspond to said training input, then said creating means spatially adjusts said temporary neuron to create said new neuron; said creating means selects at least one of said temporary neuron axes; said creating means calculates the distances along each of said selected temporary neuron axes from the center of said temporary neuron to said existing feature vector; and said creating means reduces said selected temporary neuron axes by amounts proportional to said distances and the lengths of said selected temporary neuron axes to create said new neuron.

Claim 45

The training apparatus of claim 39, wherein said training input is representative of a character.

Claim 46

The training apparatus of claim 39, wherein said information representative of said input comprises a feature vector.

Claim 47

The training apparatus of claim 41, wherein said feature vector comprises a feature element, wherein said feature element is a Grid feature element or a Hadamard feature element.

Claim 48

The training apparatus of claim 39, wherein said new neuron is a hyper-ellipse or a hyper-rectangle in k-dimensional feature space, where k is greater than or equal to two.

Claim 49

The training apparatus of claim 39, wherein said feature space comprises two or more feature-space axes, and wherein at least one of said neuron axes is parallel to one of said feature-space axes.

Claim 50

The training apparatus of claim 39, wherein said feature space comprises two or more feature-space axes, and wherein at least one of said neuron axes is parallel to none of said feature-space axes.

Claim 51

The training apparatus of claim 39, wherein said creating means selects all of said temporary neuron axes for said reduction.

Claim 52

The training apparatus of claim 39, wherein said creating means selects only one of said temporary neuron axes, said creating means calculates a distance in accordance with said selected temporary neuron axis and said existing feature vector, and said creating means reduces said selected temporary neuron axis by said distance to create said new neuron.

Claim 53

A training apparatus for adjusting a neuron, comprising: generating means for generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; and adjusting means for spatially adjusting said neuron, if said neuron encompasses said feature vector and said neuron does not correspond to said training input, wherein: said adjusted neuron comprises a boundary defined by two or more adjusted neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said neuron is in a feature space comprising an existing feature vector; said neuron comprises a boundary defined by two or more neuron axes; said adjusting means selects at least one of said neuron axes; said adjusting means calculates the distances along each of said selected neuron axes from the center of said neuron to said existing feature vector; and said adjusting means reduces said selected neuron axes by amounts proportional to said distances and the lengths of said selected neuron axes to create said adjusted neuron.

Claim 54

A training apparatus for adjusting a neuron, comprising: generating means for generating a feature vector representative of a training input, wherein said training input corresponds to one of a plurality of possible outputs; and adjusting means for spatially adjusting said neuron, if said neuron encompasses said feature vector and said neuron does not correspond to said training input, wherein: said adjusted neuron comprises a boundary defined by two or more adjusted neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said neuron is in a feature space comprising an existing feature vector; said neuron comprises a boundary defined by two or more neuron axes; said adjusting means selects at least one of said neuron axes; said adjusting means calculates the distances along each of said selected neuron axes from the center of said neuron to said existing feature vector; and said adjusting means reduces said selected neuron axes by amounts proportional to said distances and the lengths of said selected neuron axes to create said adjusted neuron.

Claim 55

The training apparatus of claim 48, wherein said training input is representative of a character.

Claim 56

The training apparatus of claim 48, wherein said information representative of said input comprises a feature vector.

Claim 57

The training apparatus of claim 50, wherein said feature vector comprises a feature element, wherein said feature element is a Grid feature element or a Hadamard feature element.

Claim 58

The training apparatus of claim 48, wherein said neuron is a hyper-ellipse or a hyper-rectangle in k-dimensional feature space, where k is greater than or equal to two.

Claim 59

The training apparatus of claim 48, wherein said feature space comprises two or more feature-space axes, and wherein at least one of said adjusted neuron axes is parallel to one of said feature-space axes.

Claim 60

The training apparatus of claim 48, wherein said feature space comprises two or more feature-space axes, and wherein at least one of said adjusted neuron axes is parallel to none of said feature-space axes.

Claim 61

The training apparatus of claim 48, wherein said adjusting means selects all of said neuron axes for said reduction.

Claim 62

The training apparatus of claim 48, wherein said adjusting means selects only one of said neuron axes, said adjusting means calculates a distance in accordance with said selected neuron axis and said existing feature vector, and said adjusting means reduces said selected neuron axis by said distance to create said adjusted neuron.

Claim 63

The training method of claim 20, wherein step (c) comprises the step of spatially adjusting said neuron to exclude said feature vector.

Claim 64

The training apparatus of claim 48, wherein said adjusting means spatially adjusts said neuron to exclude said feature vector.

Claim 65

A classification method for classifying an input into one of a plurality of possible outputs, comprising the steps of: (a) comparing information representative of said input to a neuron, wherein: said neuron comprises a boundary defined by two or more neuron axes; and the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; and (b) selecting one of said possible outputs as corresponding to said input in accordance with the comparison of step (a), wherein: step (a) comprises the step of comparing information representative of said input to a plurality of neurons; each neuron of said plurality of neurons comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said information representative of said input comprises a feature vector; step (a) further comprises the step of determining distance measures from said feature vector to each of said neurons; and step (b) comprises the steps of: (i) selecting a neuron of said plurality of neurons having the smallest distance measure of said distance measures; and (ii) selecting a possible output of said plurality of possible outputs that is associated with said selected neuron as corresponding to said input.

Claim 66

A classification method for classifying an input into one of a plurality of possible outputs, comprising the steps of: (a) comparing information representative of said input to a neuron, wherein: said neuron comprises a boundary defined by two or more neuron axes; and the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; and (b) selecting one of said possible outputs as corresponding to said input in accordance with the comparison of step (a), wherein: step (a) comprises the step of comparing information representative of said input to a plurality of neurons; each neuron of said plurality of neurons comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said information representative of said input comprises a feature vector; step (a) further comprises the step of determining distance measures from said feature vector to each of said neurons; and step (b) comprises the steps of: (i) selecting a neuron of said plurality of neurons having the smallest distance measure of said distance measures; and (ii) selecting a possible output of said plurality of possible outputs that is associated with said selected neuron as corresponding to said input.

Claim 67

The classification method of claim 59, wherein said input is representative of a character.

Claim 68

The classification method of claim 59, wherein said information representative of said input comprises a feature vector.

Claim 69

The classification method of claim 61, wherein said feature vector comprises a feature element, wherein said feature element is a Grid feature element or a Hadamard feature element.

Claim 70

The classification method of claim 61, wherein step (a) comprises the step of determining whether said neuron encompasses said feature vector.

Claim 71

The classification method of claim 61, wherein step (a) comprises the step of determining a distance measure from said feature vector to said neuron.

Claim 72

The classification method of claim 59, wherein said neuron is a hyper-ellipse or a hyper-rectangle in k-dimensional feature space, where k is greater than or equal to two.

Claim 73

The classification method of claim 59, wherein said neuron is in a feature space comprising two or more feature-space axes, wherein at least one of said neuron axes is parallel to one of said feature-space axes.

Claim 74

The classification method of claim 59, wherein said neuron is in a feature space comprising two or more feature-space axes, wherein at least one of said neuron axes is parallel to none of said feature-space axes.

Claim 75

A classification apparatus for classifying an input into one of a plurality of possible outputs, comprising: comparing means for comparing information representative of said input to a neuron, wherein: said neuron comprises a boundary defined by two or more neuron axes; and the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; and selecting means for selecting one of said possible outputs as corresponding to said input in accordance with the comparison by said comparing means, wherein: said comparing means compares information representative of said input to a plurality of neurons; each neuron of said plurality of neurons comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said information representative of said input comprises a feature vector; said comparing means determines distance measures from said feature vector to each of said neurons; said selecting means selects a neuron of said plurality of neurons having the smallest distance measure of said distance measures; and said selecting means selects a possible output of said plurality of possible outputs that is associated with said selected neuron as corresponding to said input.

Claim 76

A classification apparatus for classifying an input into one of a plurality of possible outputs, comprising: comparing means for comparing information representative of said input to a neuron, wherein: said neuron comprises a boundary defined by two or more neuron axes; and the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; and selecting means for selecting one of said possible outputs as corresponding to said input in accordance with the comparison by said comparing means, wherein: said comparing means compares information representative of said input to a plurality of neurons; each neuron of said plurality of neurons comprises a boundary defined by two or more neuron axes; the length of at least one of said two or more neuron axes differs from the length of at least one other of said two or more neuron axes; said information representative of said input comprises a feature vector; said comparing means determines distance measures from said feature vector to each of said neurons; said selecting means selects a neuron of said plurality of neurons having the smallest distance measure of said distance measures; and said selecting means selects a possible output of said plurality of possible outputs that is associated with said selected neuron as corresponding to said input.

Claim 77

The classification apparatus of claim 68, wherein said input is representative of a character.

Claim 78

The classification apparatus of claim 68, wherein said information representative of said input comprises a feature vector.

Claim 79

The classification apparatus of claim 70, wherein said feature vector comprises a feature element, wherein said feature element is a Grid feature element or a Hadamard feature element.

Claim 80

The classification apparatus of claim 70, wherein said comparing means determines whether said neuron encompasses said feature vector.

Claim 81

The classification apparatus of claim 70, wherein said comparing means determines a distance measure from said feature vector to said neuron.

Claim 82

The classification apparatus of claim 68, wherein said neuron is a hyper-ellipse or a hyper-rectangle in k-dimensional feature space, where k is greater than or equal to two.

Claim 83

The classification apparatus of claim 68, wherein said neuron is in a feature space comprising two or more feature-space axes, wherein at least one of said neuron axes is parallel to one of said feature-space axes.

Claim 84

The classification apparatus of claim 68, wherein said neuron is in a feature space comprising two or more feature-space axes, wherein at least one of said neuron axes is parallel to none of said feature-space axes.