Structurally Layered Representation Learning: Towards Deep Learning Through Genetic Programming

被引:13
|
作者
Rodriguez-Coayahuitl, Lino [1 ]
Morales-Reyes, Alicia [1 ]
Escalante, Hugo Jair [1 ]
机构
[1] Inst Nacl Astrofis Opt & Electr, Puebla 72840, Mexico
来源
GENETIC PROGRAMMING (EUROGP 2018) | 2018年 / 10781卷
关键词
Representation learning; Deep learning; Feature extraction; Genetic programming; Evolutionary machine learning; CLASSIFICATION;
D O I
10.1007/978-3-319-77553-1_17
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce a novel method for representation learning based on genetic programming (GP). Inspired into the way that deep neural networks learn descriptive/discriminative representations from raw data, we propose a structurally layered representation that allows GP to learn a feature space from large scale and high dimensional data sets. Previous efforts from the GP community for feature learning have focused on small data sets with a few input variables, also, most approaches rely on domain expert knowledge to produce useful representations. In this paper, we introduce the structurally layered GP formulation, together with an efficient scheme to explore the search space and show that this framework can be used to learn representations from large data sets of high dimensional raw data. As case of study we describe the implementation and experimental evaluation of an autoencoder developed under the proposed framework. Results evidence the benefits of the proposed framework and pave the way for the development of deep genetic programming.
引用
收藏
页码:271 / 288
页数:18
相关论文
共 50 条
  • [31] Transfer learning in constructive induction with Genetic Programming
    Munoz, Luis
    Trujillo, Leonardo
    Silva, Sara
    GENETIC PROGRAMMING AND EVOLVABLE MACHINES, 2020, 21 (04) : 529 - 569
  • [32] Genetic programming approaches to learning fair classifiers
    La Cava, William
    Moore, Jason H.
    GECCO'20: PROCEEDINGS OF THE 2020 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2020, : 967 - 975
  • [33] LEARNING TO ASSEMBLE CLASSIFIERS VIA GENETIC PROGRAMMING
    Acosta-Mendoza, Niusvel
    Morales-Reyes, Alicia
    Escalante, Hugo Jair
    Gago-Alonso, Andres
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2014, 28 (07)
  • [34] PAC Learning and Genetic Programming
    Koetzing, Timo
    Neumann, Frank
    Soephel, Reto
    GECCO-2011: PROCEEDINGS OF THE 13TH ANNUAL GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2011, : 2091 - 2096
  • [35] Dynamic learning in genetic programming
    Chiu, CC
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL I AND II, 1999, : 416 - 422
  • [36] Genetic Programming for Malignancy Diagnosis From Breast Cancer Histopathological Images: A Feature Learning Approach
    Ul Ain, Qurrat
    Al-Sahaf, Harith
    Xue, Bing
    Zhang, Mengjie
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2025,
  • [37] A hybrid framework for glaucoma detection through federated machine learning and deep learning models
    Aljohani, Abeer
    Aburasain, Rua Y.
    BMC MEDICAL INFORMATICS AND DECISION MAKING, 2024, 24 (01)
  • [38] A Comparison Study Between Deep Learning and Genetic Programming Application in Cart Pole Balancing Problem
    Miranda, Icaro Marcelino
    Ladeira, Marcelo
    Aranha, Claus de Castro
    2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2018, : 1657 - 1663
  • [39] STATE REPRESENTATION LEARNING FOR EFFECTIVE DEEP REINFORCEMENT LEARNING
    Zhao, Jian
    Zhou, Wengang
    Zhao, Tianyu
    Zhou, Yun
    Li, Houqiang
    2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2020,
  • [40] DEEP LEARNING OF FEATURE REPRESENTATION WITH MULTIPLE INSTANCE LEARNING FOR MEDICAL IMAGE ANALYSIS
    Xu, Yan
    Mo, Tao
    Feng, Qiwei
    Zhong, Peilin
    Lai, Maode
    Chang, Eric I-Chao
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,