Quaternion-based Deep Belief Networks fine-tuning

被引:19
|
作者
Papa, Joao Paulo [1 ]
Rosa, Gustavo H. [1 ]
Pereira, Danillo R. [1 ]
Yang, Xin-She [2 ]
机构
[1] Sao Paulo State Univ, Dept Comp, Av Eng Luiz Edmundo Carrijo Coube 14-01, BR-17033360 Bauru, SP, Brazil
[2] Middlesex Univ, Sch Sci & Technol, London NW4 4BT, England
基金
巴西圣保罗研究基金会;
关键词
Deep Belief Networks; Quaternion; Harmony Search; HARMONY SEARCH ALGORITHM; LEARNING ALGORITHM; NEURAL-NETWORKS;
D O I
10.1016/j.asoc.2017.06.046
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning techniques have been paramount in the last years, mainly due to their outstanding results in a number of applications. In this paper, we address the issue of fine-tuning parameters of Deep Belief Networks by means of meta-heuristics in which real-valued decision variables are described by quaternions. Such approaches essentially perform optimization in fitness landscapes that are mapped to a different representation based on hypercomplex numbers that may generate smoother surfaces. We therefore can map the optimization process onto a new space representation that is more suitable to learning parameters. Also, we proposed two approaches based on Harmony Search and quaternions that outperform the state-of-the-art results obtained so far in three public datasets for the reconstruction of binary images. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:328 / 335
页数:8
相关论文
共 50 条
  • [1] Fine-tuning Deep Belief Networks using Harmony Search
    Papa, Joao Paulo
    Scheirer, Walter
    Cox, David Daniel
    APPLIED SOFT COMPUTING, 2016, 46 : 875 - 885
  • [2] Fine-Tuning Based Deep Convolutional Networks for Lepidopterous Genus Recognition
    Carvajal, Juan A.
    Romero, Dennis G.
    Sappa, Angel D.
    PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2016, 2017, 10125 : 467 - 475
  • [3] Deep Feature Extraction Based Fine-Tuning
    Oksuz, Cosku
    Gullu, M. Kemal
    2020 28TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2020,
  • [4] No Fine-Tuning, No Cry: Robust SVD for Compressing Deep Networks
    Tukan, Murad
    Maalouf, Alaa
    Weksler, Matan
    Feldman, Dan
    SENSORS, 2021, 21 (16)
  • [5] Event Recognition on Images by Fine-Tuning of Deep Neural Networks
    Yudin, Dmitry
    Zeno, Bassel
    PROCEEDINGS OF THE SECOND INTERNATIONAL SCIENTIFIC CONFERENCE INTELLIGENT INFORMATION TECHNOLOGIES FOR INDUSTRY (IITI'17), VOL 1, 2018, 679 : 479 - 487
  • [6] Twice fine-tuning deep neural networks for paraphrase identification
    Ko, Bowon
    Choi, Ho-Jin
    ELECTRONICS LETTERS, 2020, 56 (09) : 444 - 446
  • [7] Fine-Tuning Deep Neural Networks in Continuous Learning Scenarios
    Kaeding, Christoph
    Rodner, Erik
    Freytag, Alexander
    Denzler, Joachim
    COMPUTER VISION - ACCV 2016 WORKSHOPS, PT III, 2017, 10118 : 588 - 605
  • [8] Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
    Ju, Haotian
    Li, Dongyue
    Zhang, Hongyang R.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022, : 10431 - 10461
  • [9] Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition
    Jung, Heechul
    Lee, Sihaeng
    Yim, Junho
    Park, Sunjeong
    Kim, Junmo
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 2983 - 2991
  • [10] Comparison of Fine-Tuning and Extension Strategies for Deep Convolutional Neural Networks
    Pittaras, Nikiforos
    Markatopoulou, Foteini
    Mezaris, Vasileios
    Patras, Ioannis
    MULTIMEDIA MODELING (MMM 2017), PT I, 2017, 10132 : 102 - 114