Evolving Character-Level DenseNet Architectures Using Genetic Programming

被引:4
|
作者
Londt, Trevor [1 ]
Gao, Xiaoying [1 ]
Andreae, Peter [1 ]
机构
[1] Victoria Univ Wellington, Sch Engn & Comp Sci, Wellington, New Zealand
来源
APPLICATIONS OF EVOLUTIONARY COMPUTATION, EVOAPPLICATIONS 2021 | 2021年 / 12694卷
关键词
Character-level DenseNet; Evolutionary deep learning; Genetic programming; Text classification;
D O I
10.1007/978-3-030-72699-7_42
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Densely Connected Convolutional Networks (DenseNet) have demonstrated impressive performance on image classification tasks, but limited research has been conducted on using character-level DenseNet (char-DenseNet) architectures for text classification tasks. It is not clear what DenseNet architectures are optimal for text classification tasks. The iterative task of designing, training and testing of char-DenseNets is a time consuming task that requires expert domain knowledge. Evolutionary deep learning (EDL) has been used to automatically design CNN architectures for the image classification domain, thereby mitigating the need for expert domain knowledge. This study demonstrates the first work on using EDL to evolve char-DenseNet architectures for text classification tasks. A novel genetic programming-based algorithm (GP-Dense) coupled with an indirect-encoding scheme, facilitates the evolution of performant char-DenseNet architectures. The algorithm is evaluated on two popular text datasets, and the best-evolved models are benchmarked against four current state-of-the-art character-level CNN and DenseNet models. Results indicate that the algorithm evolves performant models for both datasets that outperform two of the state-of-the-art models in terms of model accuracy and three of the stateof-the-art models in terms of parameter size.
引用
收藏
页码:665 / 680
页数:16
相关论文
共 50 条
  • [21] Character-level Adversarial Samples Generation Approach for Chinese Text Classification
    Zhang, Shunxiang
    Wu, Houyue
    Zhu, Guangli
    Xu, Xin
    Su, Mingxing
    JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2023, 45 (06) : 2226 - 2235
  • [22] Japanese Text Classification by Character-level Deep ConvNets and Transfer Learning
    Sato, Minato
    Orihara, Ryohei
    Sei, Yuichi
    Tahara, Yasuyuki
    Ohsuga, Akihiko
    ICAART: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 2, 2017, : 175 - 184
  • [23] Evolving choice structures for genetic programming
    Wang, Shuaiqiang
    Ma, Jun
    Liu, Jiming
    Niu, Xiaofei
    INFORMATION PROCESSING LETTERS, 2010, 110 (20) : 871 - 876
  • [24] Evolving text classifiers with genetic programming
    Hirsch, L
    Saeedi, M
    Hirsch, R
    GENETIC PROGRAMMING, PROCEEDINGS, 2004, 3003 : 309 - 317
  • [25] Evolving Frame Splitters by Genetic Programming
    Xie, Feng
    Song, Andy
    2012 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2012,
  • [26] Evolving Distributed Algorithms With Genetic Programming
    Weise, Thomas
    Tang, Ke
    IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2012, 16 (02) : 242 - 265
  • [27] Evolving an emotion recognition module for an intelligent agent using genetic programming and a genetic algorithm
    Yusuf, Rahadian
    Sharma, Dipak G.
    Tanev, Ivan
    Shimohara, Katsunori
    ARTIFICIAL LIFE AND ROBOTICS, 2016, 21 (01) : 85 - 90
  • [28] Weakly-supervised character-level convolutional neural networks for text classification
    Liu, Yongsheng
    Chen, Wenyu
    Niyongabo, Rubungo Andre
    Qu, Hong
    Miao, Kebin
    Wei, Feng
    DEVELOPMENTS OF ARTIFICIAL INTELLIGENCE TECHNOLOGIES IN COMPUTATION AND ROBOTICS, 2020, 12 : 701 - 708
  • [29] Character preclassification based on genetic programming
    De Stefano, C
    Della Cioppa, A
    Marcelli, A
    PATTERN RECOGNITION LETTERS, 2002, 23 (12) : 1439 - 1448
  • [30] EVOLVING ROBUST ROBOT CONTROLLERS FOR CORRIDOR FOLLOWING USING GENETIC PROGRAMMING
    Wyns, Bart
    Bonte, Bert
    Boullart, Luc
    ICAART 2010: PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1: ARTIFICIAL INTELLIGENCE, 2010, : 443 - 446