Analytical form of Fisher information matrix of bipoloar-activation-function-based multilayer perceptrons

被引：0
|
作者：
Guo, Weili [1 ,2 ,3 ]
Xie, Liping [3 ]
Fu, Zhenyong [1 ,2 ]
Guo, Jianhui [1 ,2 ]
Pang, Guochen [4 ]
Yang, Jian [1 ,2 ]
机构：
[1] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Minist Educ, PCA Lab,Key Lab Intelligent Percept & Syst High D, Nanjing, Peoples R China
[2] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Jiangsu Key Lab Image & Video Understanding Socia, Nanjing, Peoples R China
[3] Southeast Univ, Sch Automat, Key Lab Measurement & Control CSE, Minist Educ, Nanjing, Peoples R China
[4] Linyi Univ, Sch Automat & Elect Engn, Linyi, Shandong, Peoples R China
来源：
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | 2020年
关键词：
Fisher information matrix; multilayer perceptrons; singularity; bipolar error function; feedforward neural networks; GRADIENT LEARNING ALGORITHMS; NATURAL GRADIENT; DYNAMICS; SINGULARITIES;
D O I：
10.1109/ijcnn48605.2020.9207059
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
For the widely used multilayer perceptrons (MLPs), the existed singularities in the parameter space have seriously affected the learning dynamics of MLPs, which cause several singular learning behaviors. Since the Fisher information matrix (FIM) plays a significant role in analyzing the singular learning dyanmics of MLPs, it is very worthy to obtain the analytical form of FIM to do further investigation. In this paper, by choosing the bipolar error function as the activation function, the analytical form of FIM are obtained, where the validity of the obtained results are verified by taking three experiments.
引用
收藏
页数：8
相关论文
共 50 条
  • [31] Sequential Model-Based A-Optimal Design of Experiments When the Fisher Information Matrix Is Noninvertible
    Shahmohammadi, Ali
    McAuley, Kimberley B.
    INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2019, 58 (03) : 1244 - 1261
  • [32] Experimental design for optimal parameter estimation of an enzyme kinetic process based on the analysis of the Fisher information matrix
    Lindner, PFO
    Hitzmann, B
    JOURNAL OF THEORETICAL BIOLOGY, 2006, 238 (01) : 111 - 123
  • [33] Mean-squared-error-based method for parameter ranking and selection with noninvertible fisher information matrix
    Eghtesadi, Zahra
    McAuley, Kimberley B.
    AICHE JOURNAL, 2016, 62 (04) : 1112 - 1125
  • [34] Optimal design of experiment based on the Wiener degradation model with covariate using conditional Fisher information matrix
    Osintseva, Evgeniya A.
    Chimitova, Ekaterina, V
    VESTNIK TOMSKOGO GOSUDARSTVENNOGO UNIVERSITETA-UPRAVLENIE VYCHISLITELNAJA TEHNIKA I INFORMATIKA-TOMSK STATE UNIVERSITY JOURNAL OF CONTROL AND COMPUTER SCIENCE, 2024, (67):
  • [35] Evaluation of Fisher Information Matrix-Based Methods for Fast Assessment of Image Quality in Pinhole SPECT
    Pato, Lara R. V.
    Vandenberghe, Stefaan
    Vandeghinste, Bert
    Van Holen, Roel
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2015, 34 (09) : 1830 - 1842
  • [36] Optimization of metformin HCl 500 mg sustained release matrix tablets using artificial neural network (ANN) based on multilayer perceptrons (MLP) model
    Mandal, Uttarn
    Gowda, Veeran
    Ghosh, Animesh
    Bose, Aturbandeep
    Bhaumik, Uttam
    Chatterjee, Bappaditya
    Pal, Tapan Kumar
    CHEMICAL & PHARMACEUTICAL BULLETIN, 2008, 56 (02) : 150 - 155
  • [37] Frequency response function FE model updating using multiperturbed analytical models and information density matrix
    Ibrahim, SR
    Teichert, W
    Brunner, O
    IMAC - PROCEEDINGS OF THE 16TH INTERNATIONAL MODAL ANALYSIS CONFERENCE, VOLS 1 AND 2, 1998, 3243 : 1068 - 1074
  • [38] Systematic identifiability study based on the Fisher Information Matrix for reducing the number of parameters calibration of an activated sludge model
    Cunha Machado, Vinicius
    Tapia, Gladys
    Gabriel, David
    Lafuente, Javier
    Antonio Baeza, Juan
    ENVIRONMENTAL MODELLING & SOFTWARE, 2009, 24 (11) : 1274 - 1284
  • [39] 3D Head-Mounted Antenna Array Architecture Optimization based on the Fisher Information Matrix
    Poirier-Quinot, D.
    Duvaut, P.
    Girardeau, L.
    Katz, B. F. G.
    IV INTERNATIONAL CONGRESS ON ULTRA MODERN TELECOMMUNICATIONS AND CONTROL SYSTEMS 2012 (ICUMT), 2012, : 135 - 142
  • [40] Variance Prediction in SPECT Reconstruction Based on the Fisher Information Using a Novel Angular Blurring Algorithm for Computation of the System Matrix
    Bousse, Alexandre
    Erlandsson, Kjell
    Fuin, Niccolo
    Salvado, Debora
    Hutton, Brian F.
    2013 IEEE NUCLEAR SCIENCE SYMPOSIUM AND MEDICAL IMAGING CONFERENCE (NSS/MIC), 2013,
12345