Locally Weighted ELM
Download
Report
Transcript Locally Weighted ELM
1
Experimental Results
ELM
Weighted ELM
Locally Weighted ELM
Problem
2
All training data are randomly chosen
Targets are normalize -1 to 1
Features are normalize 0 to 1
Using RMSE criterion
K
RMSE
( yˆi yi ) 2
i 1
K
3
sin(x)
Sinc function:
X=-10:0.05:10 x
Train:351
Test:50
(hidden neuron, h, k)
Original ELM Weighted ELM
(10)
(10,0.01)
1.95E-1
9.41E-5
Locally
Weighted
ELM
(10,1,20)
1.53E-4
4
5
Function: y 1.1 (1 x 2x ) e
X=-5:0.05:5
Train:151
Test:50
(hidden neuron, h, k)
2
x2 / 2
Original
ELM
(10)
Weighted
ELM
(10,0.01)
Locally
Weighted
ELM
(10,1,20)
T2FNN
2.81E-1
1.39E-4
8.15E-4
1.3E-3
6
7
x22
3
y x1 e
(1 x32 )
Function:
X1,x2,x3=-1:0.005:1
Train:351
Test:50
(hidden neuron, h, k)
Original ELM Weighted ELM
(10)
(10,0.01)
1.41E-4
3.09E-6
Locally
Weighted
ELM
(10,1,20)
2.61E-5
8
Machine CPU
Feature:6
Train:100
Test:109
(hidden neuron, h, k)
Original ELM Weighted ELM
Locally
(10)
(10,0.9)
Weighted ELM
(10,1,40)
0.111342
0.103473
0.105663
9
Auto Price
Feature:15 ,1 nominal ,14 continuous
Train:80
Test:79
(hidden neuron, h, k)
Original ELM Weighted ELM
(15)
(10,0.9)
0.201255
0.189584
Locally
Weighted
ELM
(10,0.9,50)
0.193568
10
Cancer
Feature:32
Train:100
Test:94
(hidden neuron, h, k)
Original ELM Weighted ELM
(10)
(3,0.9)
0.533656
0.528415
Locally
Weighted
ELM
(3,1,40)
0.532317
11
Hβ T
g (w1x1 b1 ) g (w j x1 b j )
H
g (w x b ) g (w x b )
1 N
1
j N
j
min Hβ T
β
β (HT H)1 HT T
H : N j , hidden layer output matrix
Input
layer
hidden
layer
output
layer
β : j m , theoutput weight matrix
T : N m , target
The weights between input layer and hidden layer and the biases of neurons
in the hidden layer are randomly chosen. weight [1,1] , bias [0,1]
12
p
dn
( xa , i xn , i ) 2 , n 1 ~ N
i 1
p : the number of feature
n : then th trainingdata
a : thea th testingdata
wnn exp(0.5 (d n / h) 2 )
0
w11
W
, diagonal matrix
0 wNN
13
min W Hβ W T
β
W Hβ W T
β (( W H)T W H)1( W H)T W T
14
Ex
X [0.1;0.2;0.4]
0.4750
0.5
H 0.4502 T 0.7
0.4013
0.9
β (HT H ) 1 HT T 1.5505
0.2365
Hβ T 0.002 0.3648
0.2778
15
假設0.3為testing,target為1
d [0.2;0.1;0.1]
0
0
0.99
W 0
0.9975
0
0
0
0.9975
β ((W H)T W H) 1 ( W H)T T 1.5534
0.2355
W Hβ W T 0.0007 0.3628
0.2759
16
Find the k nearest training data to testing
data
w11 0
W , diagonal matrix
0 wkk
W Hβ W T
β (( W H)T W H)1( W H)T W T
17
Paper數據
Randomly weight and bias
The output of Nearest data
(feature selection…?)
-0.93182 0.312205 0.029309 0.061562
0
0
0
1
-0.95352 0.25826 0.060621 0.061562
0
0.019231 0.005682
2
-0.98056 0.393122 0.022044 0.03028
0
0.019231 0.005682
3
-0.97946 0.211059 0.029309 0.045921
0
0.038462 0.022727
6
-0.9493 0.204316 0.006012 0.092843
0
0.019231 0.034091
18