Born-again TSK fuzzy classifier based on knowledge distillation
This application provides a born-again TSK fuzzy classifier based on knowledge distillation. The born-again TSK fuzzy classifier based on knowledge distillation is denoted as CNNBaTSK, and a fuzzy rule of CNNBaTSK includes two parts: an antecedent part based on soft label information and a consequent part based on original data. A method for constructing the fuzzy rule of CNNBaTSK includes following steps: Step 1: taking, by the CNNBaTSK, the original data as input, obtaining a probability distribution of an output layer through a layer-by-layer neural expression, and introducing a distillation temperature to generate soft label information of DATASET; Step 2: partitioning the soft label information into five fixed fuzzy partitions to construct the fuzzy rule in a fuzzy part of the CNNBaTSK; Step 3: introducing the original data to calculate a consequent parameter, and optimizing the consequent parameter of CNNBaTSK using a non-iterative learning method.
1 . A born-again TSK fuzzy classifier based on knowledge distillation, wherein the born-again TSK fuzzy classifier based on knowledge distillation is denoted as CNNBaTSK, and a fuzzy rule of the CNNBaTSK comprises two parts: an antecedent part based on soft label information and a consequent part based on original data, and a method for constructing the fuzzy rule of the CNNBaTSK comprises following steps:
Step 1: taking, by the CNNBaTSK, the original data as input, obtaining a probability distribution of an output layer through a layer-by-layer neural expression, and introducing a distillation temperature to generate soft label information of DATASET;
Step 2: partitioning the soft label information into five fixed fuzzy partitions to construct the fuzzy rule in a fuzzy part of the CNNBaTSK;
Step 3: introducing the original data to calculate a consequent parameter, and optimizing the consequent parameter of CNNBaTSK using a non-iterative learning method.
2 . The born-again TSK fuzzy classifier based on knowledge distillation according to claim 1 , wherein in Step 2, each soft label information in different fuzzy rules have a center of {0, 0.25, 0.5, 0.75, and 1} respectively, and the soft label information is transformed into semantic interpretation to construct the fuzzy rule.
3 . The born-again TSK fuzzy classifier based on knowledge distillation according to claim 1 , wherein in Step 1, a specific method of generating the soft label information of DATASET comprises: firstly stacking multiple convolutional layers and pooling layers, in terms of layer by layer learning and generating a depth feature, the convolutional layers and the pooling layers used being disposed alternately, and then performing classification through several fully-connected layers and the output layer; the convolutional layer, the pooling layer, and the fully-connected layer are respectively denoted as a Conv layer, a Pool layer, and a FC layer;
assuming that a training dataset is X={x i , x i =(x 1 , x 2 , . . . , x n ) T , x i ∈R n , i=1, 2, . . . , N} and a label set is {tilde over (Y)}={Y i , Y i ∈{0, 1, . . . , K}, i=1, 2, . . . , N}, where n represents a sample dimension, N represents a sample quantity, and K represents a sample category; in a convolutional neural network, an output result (feature map) of a layer t is marked as Z t , where Z 0 represents the original data x i ;
in the Conv layer, a local connection method is employed to execute a convolution calculation, and then a bias be is added to the feature map, and then an activation function ƒ(⋅) is employed for a nonlinear transformation; and a calculation process for the Conv layer is as follows:
Z
t
=
j
(
W
i
⋆
Z
t
-
1
+
b
t
)
(
1
)
after the convolution calculation is completed, a nonlinear mapping of the PRelu activation function is performed, wherein a mathematical expression of the PRelu is expressed as follows:
f
(
a
)
=
{
a
,
if
a
>
0
κ
a
,
otherwise
(
2
)
wherein α represents an input variable and κ represents a slope coefficient;
in the Pool layer, a maximum value in a pooling window is selected as a result in a selected maximum pooling operation, and a pooling process can be expressed as follows:
Z
t
=
Pool
(
Z
t
-
1
)
(
3
)
after several convolution and maximum pooling operations, an extracted depth feature is input into a first FC layer; in the FC layer, all neurons between layers are connected, and the depth feature is further mapped to a new feature space to complete a classification task; calculation is performed through a weight W t and the bias b t , and a nonlinear transformation is performed using the activation function ƒ(⋅); and a calculation process is as follows:
Z
t
=
f
(
W
t
·
Z
t
-
1
+
b
t
)
(
4
)
an output layer of the convolutional neural network uses Softmax activation function, and an output thereof Z t =(z 1 , z 2 , . . . , z K ) T is transformed into a corresponding probability result E i =(e 1 , e 2 , . . . , e K ) T , wherein K represents a total number of category, and its calculation process is as follows:
e
K
=
exp
(
z
K
)
/
∑
k
=
1
K
exp
(
z
k
)
(
5
)
during the training process, a cross-entropy loss function is employed to measure a difference between the output of the convolutional neural network and a ground-truth label, and its calculation formula is as follows:
min
-
1
N
∑
i
=
1
N
∑
k
=
1
K
Y
i
,
k
log
(
e
k
(
E
i
)
)
(
6
)
the weight W t and bias b t of the convolutional neural network are iterated and optimized through an error backpropagation algorithm; a loss value of formula (6) is backpropagated from a last layer to a first layer, and parameter updating is performed according to the error of each layer; assuming that a derivative of cross-entropy loss for the weight W t is ΔW t , and a derivative of cross-entropy loss for the bias b t is Δb t , formula for parameter updating are expressed as follows:
W
t
l
=
W
t
l
-
θΔ
W
t
l
-
1
(
7
)
b
t
l
=
b
t
l
-
θΔ
b
t
l
-
1
(
8
)
wherein l represents a training iteration epoch and θ represents a learning rate;
in order to facilitate the distinction, a probability distribution of the output layer softened by the distillation temperature T is called the soft label information s i =(s 1 , s 2 , . . . , s K ) T , and its calculation method is as follows:
s
K
=
exp
(
z
K
/
T
)
/
∑
k
=
1
K
exp
(
z
k
/
T
)
(
9
)
in a binary-class classification task, assuming that the training dataset is expressed as X={x i , x i =(x 1 , x 2 , . . . , x n ) T , x i ∈R n , i=1, 2, . . . , N}, {tilde over (Y)}={Y i , Y i , ∈{0,1}, i=1, 2, . . . , N} is a ground-truth label vector of the binary-class classification task; the probability distribution of the output layer E i =(e 1 , e 2 ) T is transformed into the soft label information S={s i =(s 1 , s 2 ) T , s k ∈[0,1], k=1,2, i=1, 2, . . . , N} after introducing the distillation temperature T, wherein the sum of all probabilities in each sample is 1, that is, s 1 +s 2 =1.
4 . The born-again TSK fuzzy classifier based on knowledge distillation according to claim 3 , wherein in Step 2, the CNNBaTSK adopts following fuzzy rules:
In
rule
m
:
IF
s
1
is
*
^
s
2
is
*
THEN
y
m
=
p
0
m
+
p
1
m
x
1
+
p
2
m
x
2
+
…
+
p
n
m
x
n
.
m
=
1
,
2
,
…
,
M
(
10
)
wherein * denotes the membership of fuzzy partition, M is the total number of fuzzy rules and ∧ denotes a fuzzy conjunction operator, and the consequent part adopts a linear function of the input data x i ;
the antecedent part of the soft label information is taken into five fixed fuzzy partitions, wherein each fuzzy partition has a center of
c
d
m
∈
{
0
,
0.25
,
0.5
,
0.75
,
1
}
,
and the kernel width
σ
d
m
is set at a random positive value which is between 0 and 1; then, a Gaussian membership function as a fuzzy membership function is applied to estimate a membership of each rule, and its calculation method is as follows:
μ
m
(
s
i
,
d
)
=
exp
(
-
(
s
i
,
d
-
c
d
m
)
2
/
2
σ
d
m
)
(
11
)
μ
m
(
s
i
)
=
∏
d
=
1
2
μ
m
(
s
i
,
d
)
μ
m
(
s
i
)
=
∏
d
=
1
2
μ
m
(
s
i
,
d
)
(
12
)
a normalized membership function is formulated as follows:
μ
~
m
(
s
i
)
=
μ
m
(
s
i
)
/
∑
m
′
=
1
M
μ
m
′
(
s
i
)
(
13
)
therefore, the output {tilde over (y)} i of the CNNBaTSK can be expressed as:
y
~
i
=
∑
m
=
1
M
μ
~
m
(
s
i
)
y
m
(
14
)
making:
p
m
=
(
p
0
m
,
p
1
m
,
…
,
p
n
m
)
T
(
15
)
P
=
(
(
p
l
)
T
,
(
p
2
)
T
,
…
,
(
p
m
)
T
)
T
(
16
)
q
i
m
=
μ
~
m
(
s
i
)
(
l
,
x
i
)
T
(
17
)
Q
l
=
(
(
q
i
l
)
T
,
(
q
i
2
)
T
,
…
,
(
q
i
m
)
T
)
T
(
18
)
the output {tilde over (y)} i of the CNNBaTSK may be expressed as:
y
~
i
=
Q
i
T
P
.
(
19
)
5 . The born-again TSK fuzzy classifier based on knowledge distillation according to claim 4 , wherein in Step 3, a specific method for optimizing the consequent parameter of the CNNBaTSK is as follows:
an objective function is designed to balance the ground-truth label and the soft label information, and a following objective function for optimization is proposed:
min
1
2
∑
N
i
=
1
ς
i
2
+
α
2
P
2
2
+
β
2
∑
i
=
1
N
ξ
t
2
(
20
)
s
.
t
.
{
Q
i
T
P
-
Y
i
=
ς
i
Q
i
T
P
-
s
i
,
2
=
ξ
i
,
i
=
1
,
2
,
…
,
N
wherein P is the consequent parameter of the fuzzy rule, α and β are regularization factors, ζ i is a deviation between the prediction output and the ground-truth label, ξ i is a deviation between the prediction output and the soft label information; based on s 1 +s 2 =1 and the ground-truth label, index of the probability s 2 is matched with the ground-truth label;
a Lagrangian optimization formula of the objective function can be expressed as:
L
(
P
,
ς
,
ξ
,
τ
,
v
)
=
1
2
ς
2
2
+
α
2
P
2
2
+
β
2
ξ
2
2
-
τ
(
Q
~
P
-
Y
~
-
ς
)
-
v
(
Q
~
P
-
S
~
-
ξ
)
(
21
)
wherein ζ=(ζ 1 , ζ 2 , . . . , ζ N ) T , ξ=(ξ 1 , ξ 2 , . . . , ξ N ) T , τ=(τ 1 , τ 2 , . . . , τ N ) T and ν=(ν 1 , ν 2 , . . . , ν N ) T are Lagrangian multipliers with equality constraints, and an input matrix is denoted by {tilde over (Q)}=(Q 1 , Q 2 , . . . , Q N ) T ;
the consequent parameter P is calculated by setting a derivative gradient of the Lagrangian optimization formula with respect to (P, ζ, ξ, τ, ν) equal to be zero, resulting in following KKT optimality conditions:
{
∂
L
∂
P
⇒
α
P
T
=
τ
Q
~
+
v
Q
~
a
L
∂
ς
⇒
ς
T
+
τ
=
0
∂
L
∂
ξ
⇒
β
ξ
T
+
v
=
0
∂
L
∂
τ
⇒
Q
~
P
-
Y
~
-
ς
=
0
∂
L
∂
v
⇒
Q
~
P
-
S
~
-
ξ
=
0
(
22
)
yielding:
{
τ
=
-
(
Q
~
P
-
Y
~
)
T
v
=
-
β
(
Q
~
P
-
S
~
)
T
α
P
T
=
-
(
Q
~
P
-
Y
~
)
T
Q
~
-
β
(
Q
~
P
-
S
~
)
T
Q
~
(
23
)
therefore, an optimal analytical solution can be expressed as:
P
=
(
α
I
+
(
1
+
β
)
Q
˜
T
Q
˜
)
-
1
(
Q
˜
T
Y
˜
+
β
Q
˜
T
S
˜
)
(
24
)
wherein I denotes an identity matrix.
6 . The born-again TSK fuzzy classifier based on knowledge distillation according to claim 1 , wherein a learning algorithm of CNNBaTSK has inputs comprising: training dataset X={x i , x i =(x 1 , x 2 , . . . , x n ) T , x i ∈R n , i=1, 2 . . . , N} and {tilde over (Y)}={Y i , Y i ∈{0, 1, . . . , K}, i=1, 2, . . . , N} and a maximum iteration epoch {tilde over (l)}, initial learning rate θ, distillation temperature T, regularization factors α and β, testing sample x test of the convolutional neural network; outputs comprising CNNBaTSK after completion of training, and the output {tilde over (y)} test of the testing sample; the learning algorithm of the CNNBaTSK comprises two stages as follows:
S1: training stage:
S10: initialization: initializing W t and b t with random numbers, and proceeding step S11 to step S13 sequentially within a range of the maximum iteration epoch {tilde over (l)};
S11: inputting training samples X={x i , x i =x 1 , x 2 , . . . , x n ) T , x i ∈R n , i=1, 2, . . . , N}, and performing a convolutional and pooling operation on the training samples through the Conv layer and the Pool layer to extract depth features;
S12: calculating a probability that the sample belongs to each label at the FC layer;
S13: performing error backpropagation on 1D-CNN according to a cross-entropy loss function formula;
S14: generating a probability distribution E i =(e 1 , e 2 ) T of the output layer after the iteration is completed;
S15: introducing the distillation temperature T and converting it into the soft label information S={s i =(s 1 ,s 2 ) T , s k ∈[0,1], k=1,2, i=1,2, . . . , N};
S16: partitioning the antecedent part into five fixed fuzzy partitions, wherein the center of each fuzzy partition is
c
d
m
∈
{
0
,
0.25
,
0.5
,
0.75
,
1
}
,
and the kernel width
σ
d
m
is set at a random positive value which is between 0 and 1;
S17: computing a normalized membership {tilde over (μ)} m (s i ) of the training sample in different rules;
S18: computing and generating Q i , wherein the output of the CNNBaTSK can be expressed as
y
~
i
=
Q
i
T
P
;
S19: computing an analytical solution for P to be: P=(αI+(1+β){tilde over (Q)} T {tilde over (Q)}) −1 ({tilde over (Q)} T {tilde over (Y)}+β{tilde over (Q)} T {tilde over (S)});
S2: testing stage:
S21: inputting a testing sample x test ;
S22: generating the probability distribution E test =(e 1 , e 2 ) T of the output layer;
S23: computing the probability distribution s test =(s 1 , s 2 ) T of the output layer of the soft label information;
S24: computing a normalized membership {tilde over (μ)} m (s i ) of the testing sample in different rules;
S25: outputting {tilde over (y)} test of the testing sample according to
y
~
test
=
Q
test
T
P
.
7 . A method for constructing a fuzzy rule for a born-again TSK fuzzy classifier based on knowledge distillation, wherein the born-again TSK fuzzy classifier based on knowledge distillation is denoted as CNNBaTSK, and the fuzzy rule of the CNNBaTSK comprises two parts: an antecedent part based on soft label information and a consequent part based on original data, and the method for constructing the fuzzy rule of the CNNBaTSK comprises following steps:
Step 1: taking, by the CNNBaTSK, the original data as input, obtaining a probability distribution of an output layer through a layer-by-layer neural expression, and introducing a distillation temperature to generate soft label information of DATASET;
Step 2: partitioning the soft label information into five fixed fuzzy partitions to construct the fuzzy rule in a fuzzy part of the CNNBaTSK;
Step 3: introducing the original data to calculate a consequent parameter, and optimizing the consequent parameter of CNNBaTSK using a non-iterative learning method.
8 . The method for constructing the fuzzy rule according to claim 7 , wherein in Step 2, each soft label information in different fuzzy rules have a center of {0, 0.25, 0.5, 0.75, and 1} respectively, and the soft label information is transformed into semantic interpretation to construct the fuzzy rule.
9 . The method for constructing the fuzzy rule according to claim 7 , wherein in Step 1, a specific method of generating the soft label information of DATASET comprises: firstly stacking multiple convolutional layers and pooling layers, in terms of layer by layer learning and generating a depth feature, the convolutional layers and the pooling layers used being disposed alternately, and then performing classification through several fully-connected layers and the output layer; the convolutional layer, the pooling layer, and the fully-connected layer are respectively denoted as a Conv layer, a Pool layer, and a FC layer;
assuming that a training dataset is X={x i , x i =(x 1 , x 2 , . . . , x n ) T , x i ∈R n , i=1, 2, . . . , N} and a label set is {tilde over (Y)}={Y i , Y i ∈{0, 1, . . . , K}, i=1, 2, . . . , N}, where n represents a sample dimension, N represents a sample quantity, and K represents a sample category; in a convolutional neural network, an output result (feature map) of a layer t is marked as Z t , where Z 0 represents the original data x i ;
in the Conv layer, a local connection method is employed to execute a convolution calculation, and then a bias be is added to the feature map, and then an activation function ƒ(⋅) is employed for a nonlinear transformation; and a calculation process for the Conv layer is as follows:
Z
t
=
f
(
W
t
*
Z
t
-
1
+
b
t
)
(
1
)
after the convolution calculation is completed, a nonlinear mapping of the PRelu activation function is performed, wherein a mathematical expression of the PRelu is expressed as follows:
f
(
a
)
=
{
a
,
if
a
>
0
κ
a
,
otherwise
(
2
)
wherein α represents an input variable and κ represents a slope coefficient;
in the Pool layer, a maximum value in a pooling window is selected as a result in a selected maximum pooling operation, and a pooling process can be expressed as follows:
Z
t
=
Pool
(
Z
t
-
1
)
(
3
)
after several convolution and maximum pooling operations, an extracted depth feature is input into a first FC layer; in the FC layer, all neurons between layers are connected, and the depth feature is further mapped to a new feature space to complete a classification task;
calculation is performed through a weight W t and the bias b t , and a nonlinear transformation is performed using the activation function ƒ(⋅); and a calculation process is as follows:
Z
t
=
f
(
W
t
·
Z
t
-
1
+
b
t
)
(
4
)
an output layer of the convolutional neural network uses Softmax activation function, and an output thereof Z t =(z 1 , z 2 , . . . , z K ) T is transformed into a corresponding probability result E i ==(e 1 , e 2 , . . . , e K ) T , wherein K represents a total number of category, and its calculation process is
e
K
=
exp
(
z
K
)
/
∑
k
=
1
K
exp
(
z
k
)
(
5
)
during the training process, a cross-entropy loss function is employed to measure a difference between the output of the convolutional neural network and a ground-truth label, and its calculation formula is as follows:
min
-
1
N
∑
i
=
1
N
∑
k
=
1
K
Y
i
,
k
log
(
e
k
(
E
i
)
)
(
6
)
the weight W t and bias b t of the convolutional neural network are iterated and optimized through an error backpropagation algorithm; a loss value of formula (6) is backpropagated from a last layer to a first layer, and parameter updating is performed according to the error of each layer; assuming that assuming that a derivative of cross-entropy loss for the weight W t is ΔW t , and a derivative of cross-entropy loss for the bias b t is Δb t , formula for parameter updating are expressed as follows:
W
t
l
=
W
t
l
-
θΔ
W
t
l
-
1
(
7
)
b
t
l
=
b
t
l
-
θΔ
b
t
l
-
1
(
8
)
wherein l represents a training iteration epoch and θ represents a learning rate;
in order to facilitate the distinction, a probability distribution of the output layer softened by the distillation temperature T is called the soft label information s i =(s 1 , s 2 , . . . , s K ) T , and its calculation method is as follows:
s
K
=
exp
(
z
K
/
T
)
/
∑
k
=
1
K
exp
(
z
k
/
T
)
(
9
)
in a binary-class classification task, assuming that the training dataset is expressed as X={x i , x i =(x 1 , x 2 , . . . , x n ) T , x i ∈R n , i=1, 2, . . . , N}, {tilde over (Y)}={Y i , Y i ∈{0,1}, i=1, 2, . . . , N} is a ground-truth label vector of the binary-class classification task; the probability distribution of the output layer E i =(e 1 , e 2 ) T is transformed into the soft label information S={s i =(s 1 , s 2 ) T , s k ∈[0,1], k=1,2, i=1, 2, . . . , N} after introducing the distillation temperature T, wherein the sum of all probabilities in each sample is 1, that is, s 1 +s 2 =1.
10 . The method for constructing the fuzzy rule according to claim 9 , wherein the Step 2, the CNNBaTSK adopts following fuzzy rules:
In
rule
m
:
IF
s
1
is
*
^
s
2
is
*
THEN
y
m
=
p
0
m
+
p
1
m
x
1
+
p
2
m
x
2
+
…
+
p
n
m
x
n
.
m
=
1
,
2
,
…
,
M
(
10
)
wherein * denotes the membership of fuzzy partition, M is the total number of fuzzy rules and ∧ denotes a fuzzy conjunction operator, and the consequent part adopts a linear function of the input data x i ;
the antecedent part of the soft label information is taken into five fixed fuzzy partitions, wherein each fuzzy partition has a center of
c
d
m
∈
{
0
,
0.25
,
0.5
,
0.75
,
1
}
,
and the kernel width
σ
d
m
is set at a random positive value which is between 0 and 1; then, a Gaussian membership function as a fuzzy membership function is applied to estimate a membership of each rule, and its calculation method is as follows:
μ
m
(
s
i
,
d
)
=
exp
(
-
(
s
i
,
d
-
c
d
m
)
2
/
2
σ
d
m
)
(
11
)
μ
m
(
s
i
)
=
∏
2
d
=
1
μ
m
(
s
i
,
d
)
μ
m
(
s
i
)
=
∏
2
d
=
1
μ
m
(
s
i
,
d
)
(
12
)
a normalized membership function is formulated as follows:
μ
~
m
(
s
i
)
=
μ
m
〈
s
i
)
/
∑
m
′
=
1
M
μ
m
′
(
s
i
)
(
13
)
therefore, the output {tilde over (y)} i of the CNNBaTSK can be expressed as:
y
~
i
=
∑
m
=
1
M
μ
~
m
(
s
i
)
y
m
(
14
)
making:
p
m
=
(
p
0
m
,
p
1
m
,
…
,
p
n
m
)
T
(
15
)
P
=
(
(
p
l
)
T
,
(
p
2
)
T
,
…
,
(
p
m
)
T
)
T
(
16
)
q
i
m
=
μ
~
m
(
s
i
)
(
l
,
x
i
)
T
(
17
)
Q
l
=
(
(
q
i
l
)
T
,
(
q
i
2
)
T
,
…
,
(
q
i
m
)
T
)
T
(
18
)
the output {tilde over (y)} i of the CNNBaTSK may be expressed as:
y
~
i
=
Q
i
T
P
.
(
19
)
11 . The method for constructing the fuzzy rule according to claim 10 , wherein in Step 3, a specific method for optimizing the consequent parameter of the CNNBaTSK is as follows:
an objective function is designed to balance the ground-truth label and the soft label information, and a following objective function for optimization is proposed:
min
1
2
∑
N
i
=
1
ς
i
2
+
α
2
P
2
2
+
β
2
∑
i
=
1
N
ξ
i
2
(
20
)
s
.
t
.
{
Q
i
T
P
-
Y
i
=
ς
i
Q
i
T
P
-
s
i
,
2
=
ξ
i
,
i
=
1
,
2
,
…
,
N
wherein P is the consequent parameter of the fuzzy rule, α and β are regularization factors, ζ i is a deviation between the prediction output and the ground-truth label, ξ i is a deviation between the prediction output and the soft label information; based on s 1 +s 2 =1 and the ground-truth label, index of the probability s 2 is matched with the ground-truth label;
a Lagrangian optimization formula of the objective function can be expressed as:
L
(
P
,
ς
,
ξ
,
τ
,
v
)
=
1
2
ς
2
2
+
α
2
P
2
2
+
β
2
ξ
2
2
-
τ
(
Q
~
P
-
Y
~
-
ς
)
-
v
(
Q
~
P
-
S
~
-
ξ
)
(
21
)
wherein ζ=(ζ 1 , ζ 2 , . . . , ζ N ) T , ξ=(ξ 1 , ξ 2 , . . . , ξ N ) T , τ=(τ 1 , τ 2 , . . . , τ N ) T and ν=(ν 1 , ν 2 , . . . , ν N ) T are Lagrangian multipliers with equality constraints, and an input matrix is denoted by {tilde over (Q)}=(Q 1 , Q 2 , . . . , Q N ) T ;
the consequent parameter P is calculated by setting a derivative gradient of the Lagrangian optimization formula with respect to (P, ζ, ξ, τ, ν) equal to be zero, resulting in following KKT optimality conditions:
{
∂
L
∂
P
⇒
α
P
T
=
τ
Q
~
+
v
Q
~
∂
L
∂
ς
⇒
ς
T
+
τ
=
0
∂
L
∂
ξ
⇒
β
ξ
T
+
v
=
0
∂
L
∂
τ
⇒
Q
~
P
-
Y
~
-
ς
=
0
∂
L
∂
v
⇒
Q
~
P
-
S
~
-
ξ
=
0
(
22
)
yielding:
{
τ
=
-
(
Q
~
P
-
Y
~
)
T
v
=
-
β
(
Q
~
P
-
S
~
)
T
α
P
T
=
-
(
Q
~
P
-
Y
~
)
T
Q
~
-
β
(
Q
~
P
-
S
~
)
T
Q
~
(
23
)
therefore, an optimal analytical solution can be expressed as:
P
=
(
α
I
+
(
1
+
β
)
Q
~
T
Q
~
)
-
1
(
Q
~
T
Y
~
+
β
Q
~
T
S
~
)
(
24
)
wherein I denotes an identity matrix.
12 . The method for constructing the fuzzy rule according to claim 7 , wherein a learning algorithm of CNNBaTSK has inputs comprising: training dataset X={x i , x i =(x 1 , x 2 , . . . , x n ) T , x i ∈R n , i=1,2 . . . , N} and {tilde over (Y)}={Y i , Y i ∈{0, 1, . . . , K}, i=1,2, . . . , N}, and a maximum iteration epoch {tilde over (l)}, initial learning rate θ, distillation temperature T, regularization factors α and β, testing sample x test of the convolutional neural network; outputs comprising CNNBaTSK after completion of training, and the output {tilde over (y)} test of the testing sample; the learning algorithm of the CNNBaTSK comprises two stages as follows:
S1: training stage:
S10: initialization: initializing W t and b t with random numbers, and proceeding step S11 to step S13 sequentially within a range of the maximum iteration epoch {tilde over (l)};
S11: inputting training samples X={x i , x i =x 1 , x 2 , . . . , x n ) T , x i ∈R n , i=1, 2, . . . , N}, and performing a convolutional and pooling operation on the training samples through the Conv layer and the Pool layer to extract depth features;
S12: calculating a probability that the sample belongs to each label at the FC layer;
S13: performing error backpropagation on 1D-CNN according to a cross-entropy loss function formula;
S14: generating a probability distribution E i =(e 1 , e 2 ) T of the output layer after the iteration is completed;
S15: introducing the distillation temperature T and converting it into the soft label information S={s i =(s 1 ,s 2 ) T , s k ∈[0,1], k=1,2, i=1,2, . . . , N};
S16: partitioning the antecedent part into five fixed fuzzy partitions, wherein the center of each fuzzy partition is
c
d
m
∈
{
0
,
0.25
,
0.5
,
0.75
,
1
}
,
and the kernel width
σ
d
m
is set at a random positive value which is between 0 and 1;
S17: computing a normalized membership {acute over (μ)} m (s i ) of the training sample in different rules;
S18: computing and generating Q i , wherein the output of the CNNBaTSK can be expressed as
y
~
i
=
Q
i
T
P
;
S19: computing an analytical solution for P to be: P=(αI+(1+β){tilde over (Q)} T {tilde over (Q)}) −1 ({tilde over (Q)} T {tilde over (Y)}+β{tilde over (Q)} T {tilde over (S)});
S2: testing stage:
S21: inputting a testing sample x test ;
S22: generating the probability distribution E test =(e 1 , e 2 ) T of the output layer;
S23: computing the probability distribution s test =(s 1 , s 2 ) T of the output layer of the soft label information;
S24: computing a normalized membership {tilde over (ρ)} m (s i ) of the testing sample in different rules;
S25: outputting {tilde over (y)} test of the testing sample according to
y
~
test
=
Q
test
T
P
.