• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
成果搜索

author:

Feng, Shuang (Feng, Shuang.) [1] | Chen, C. L. Philip (Chen, C. L. Philip.) [2] | Zhang, Chun-Yang (Zhang, Chun-Yang.) [3] (Scholars:张春阳)

Indexed by:

EI Scopus SCIE

Abstract:

We establish a fuzzy deep model called the fuzzy deep belief net (FDBN) based on fuzzy restricted Boltzmann machines (FRBMs) due to their excellent generative and discriminative properties. The learning procedure of an FDBN is divided into a pretraining phase and a subsequent fine-tuning phase. In the pretraining phase, a group of FRBMs is trained in a greedy layerwise way: the first FRBM is trained by original samples, and the average values of the left and right probabilities produced by its hidden units are treated as the training data for subsequent FRBMs. The resulting FDBN is either a generative or a discriminative model depending on the choice of training a generative or a discriminative type of FRBM on top. Then, a hybrid learning approach is proposed to fine-tune this novel fuzzy deep model: the well pretrained fuzzy parameters are first defuzzified, and the FDBN with defuzzified parameters is fine-tuned by the wake-sleep or stochastic gradient descent algorithm. This hybrid strategy not only avoids learning an intractable fuzzy neural network, but also greatly improves the classification capability of the FDBN. The experimental results on MNIST, NORB, and 15 Scene databases indicate that the FDBN with the hybrid learning approach can handle high-dimensional raw images directly. It inherits the fine nature of the FRBM and outperforms some state-of-the-art discriminative models in classification accuracy. Moreover, it shows better capability of robustness than a deep belief net when encountering noisy data.

Keyword:

Classification Databases Data models fuzzy deep model Fuzzy neural networks fuzzy restricted Boltzmann machine (FRBM) hybrid learning Neural networks Training Training data

Community:

  • [ 1 ] [Feng, Shuang]Beijing Normal Univ, Sch Appl Math, Zhuhai 519087, Peoples R China
  • [ 2 ] [Feng, Shuang]Univ Macau, Fac Sci & Technol, Macau 999078, Peoples R China
  • [ 3 ] [Chen, C. L. Philip]Univ Macau, Fac Sci & Technol, Macau 999078, Peoples R China
  • [ 4 ] [Chen, C. L. Philip]Dalian Maritime Univ, Dept Nav, Dalian 116026, Peoples R China
  • [ 5 ] [Chen, C. L. Philip]Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China
  • [ 6 ] [Zhang, Chun-Yang]Fuzhou Univ, Sch Math & Comp Sci, Fuzhou 350116, Peoples R China

Reprint 's Address:

  • [Feng, Shuang]Beijing Normal Univ, Sch Appl Math, Zhuhai 519087, Peoples R China

Show more details

Related Keywords:

Source :

IEEE TRANSACTIONS ON FUZZY SYSTEMS

ISSN: 1063-6706

Year: 2020

Issue: 7

Volume: 28

Page: 1344-1355

1 2 . 0 2 9

JCR@2020

1 0 . 7 0 0

JCR@2023

ESI Discipline: ENGINEERING;

ESI HC Threshold:132

JCR Journal Grade:1

CAS Journal Grade:1

Cited Count:

WoS CC Cited Count: 41

SCOPUS Cited Count: 43

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Online/Total:189/10227738
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1