Evolutionary Convolutional Neural Networks Using ABC

被引：17

作者：

Zhu, Wenbo ^{[1
]}

Yeh, Weichang ^{[2
]}

Chen, Jianwen ^{[1
]}

Chen, Dafeng ^{[1
]}

Li, Aiyuan ^{[1
]}

Lin, Yangyang ^{[1
]}

机构：

[1] Foshan Univ, Dept Automat, Guangyun Rd 33, Foshan, Peoples R China

[2] Natl Tsing Hua Univ, Dept Ind Engn & Engn Management, Hsinchu 300, Taiwan

来源：

ICMLC 2019: 2019 11TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND COMPUTING | 2019年

关键词：

Neuro-evolution; Hyperparameter optimization; evolutionary computation; convolutional neural networks; artificial bee colony; ALGORITHM; SELECTION; PSO;

D O I：

10.1145/3318299.3318301

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Convolutional neural networks (CNNs) have been used over the past years to solve many different artificial intelligence (AI) problems, providing significant advances in some domains and leading to state-of-the-art results. Nonetheless, the design of CNNs architecture remains to be a meticulous and cumbersome process that requires the participation of specialists in the field. In this work, we have explored the neuro-evolution application to the automatic design of CNN topologies, developing a novel solution based on Artificial Bee Colony (ABC). The MNIST dataset is used to evaluate the proposed method, which is proved being highly competitive with the state-of-the-art.

引用

页码：156 / 162

页数：7

共 25 条

[21] Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms
Thornton, Chris
Hutter, Frank
Hoos, Holger H.
Leyton-Brown, Kevin
[J]. 19TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (KDD'13), 2013, : 847 - 855
[22] Verbancsics P., 2015, P IEEE WINT C APPL C
[23] Wang SH, 2018, J MED SYST, V42, DOI [10.1007/s10916-018-0932-7, 10.1007/s10916-017-0845-x]
[24] Xie L., 2017, COMPUTER VISION PATT
[25] Young S.R., 2015, Optimizing Deep Learning Hyper-Parameters Through an Evolutionary Algorithm

← 1 2 3 →