卷积神经网络与人工水母搜索的图特征选择方法

卷积神经网络与人工水母搜索的图特征选择方法

孙林, 蔡怡文

Convolutional Neural Network and Artificial Jellyfish Search⁃based graph feature selection method

Lin Sun, Yiwen Cai

表1 10个基准测试函数的描述

Table 1 Description of ten benchmark test functions

No.	Name	Functions	Range	Optimum
f₁	Sphere	$f (x) = \sum_{i = 1}^{n} x_{i}^{2}$	$[- 5.12,5.12]$	0
f₂	Schwefel 2.22	$f (x) = \sum_{i = 1}^{n} \|x_{i}\| + \overset{n}{\prod_{i = 1}} \|x_{i}\|$	$[- 10,10]$	0
f₃	Schwefel 2.21	$f (x) = \underset{i}{m a x} (\|x_{i}\|, 1 \leq x \leq n)$	$[- 100,100]$	0
f₄	Rastrigin	$f (x) = \sum_{i = 1}^{n} [x_{i}^{2} - 10 c o s (2 π x_{i}) + 10]$	$[- 5.12,5.12]$	0
f₅	Ackley	$f (x) = - 20 e x p (- 0.2 \sqrt[]{\frac{1}{n} \sum_{i = 1}^{n} x_{i}^{2}}) - e x p (\frac{1}{n} \sum_{i = 1}^{n} c o s 2 π x_{i}) + 20 + e$	$[- 30,30]$	0
f₆	Griewank	$f (x) = \frac{1}{4000} \sum_{i = 1}^{n} x_{i}^{2} - \overset{n}{\prod_{i = 1}} c o s (x_{i} / \sqrt[]{i}) + 1$	$[- 600,600]$	0
f₇	Schwefe l1.2	$f (x) = \sum_{i = 1}^{n} {(\sum_{j = 1}^{i} x_{j})}^{2}$	$[- 100,100]$	0
f₈	Quartic	$f (x) = \sum_{i = 1}^{n} i x^{4} + r a n d o m [0,1)$	$[- 1.28,1.28]$	0
f₉	Rosenbrock	$f (x) = \sum_{i = 1}^{n} [100 {(x_{i + 1} - x_{i}^{2})}^{2} + {(x_{i} - 1)}^{2}]$	$[- 30,30]$	0
f₁₀	Penalized2	$f (x) = 0.1 \{\begin{array}{l} s i n^{2} (3 π x_{1}) + \sum_{i = 1}^{n} {(x_{i} - 1)}^{2} [1 + s i n^{2} (3 π x_{i} + 1)] + \\ {(x_{n} - 1)}^{2} [1 + s i n^{2} (2 π x_{i} + 1)] \end{array}\} + \sum_{i = 1}^{n} u (x_{i}, 5,100,4)$	$[- 50,50]$	0